System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a list of relevant web pages based on a user's query; means for analyzing content of the web pages using a generated AI and evaluating credibility; means for calculating a credibility score for each web page based on the analysis; means for adding the credibility score to search results; and means for displaying the search results including the credibility evaluation to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a huge amount of information on the Internet, and it is difficult for non-experts to judge the reliability of information obtained through search engines. This is because there are limited ways to evaluate the title of the website operator or the content itself, and there is a high risk of making decisions based on incorrect information. As a result, there is a need for effective methods to prevent users from being misled by incorrect information and to use reliable information. [Means for solving the problem]

[0005] The present invention provides a system in which, when a user enters a search query into a search engine, a server generates a list of relevant web pages, analyzes the content using a generation AI, and evaluates its reliability. Specifically, the server inputs the web page content into the generation AI, which analyzes the accuracy of technical terms and the reliability of the information source. Based on this, a reliability score is calculated and added to the search results. In addition, a concise evaluation message based on the reliability score is added and displayed on the user's device, allowing the user to easily confirm the reliability of the information. This system enables even non-experts to quickly find reliable information from search results.

[0006] A "User" is any person or entity seeking to obtain information using a search engine.

[0007] A "search engine" is a system that searches for and displays relevant web pages based on an input search query.

[0008] A "search query" is a keyword or phrase that a user enters to search for specific information.

[0009] The "server" is a computer system that receives a user's search query, searches, retrieves, and analyzes relevant web pages, and evaluates their reliability using generative AI.

[0010] A "web page" is a unit of information published on the Internet and written in HTML format.

[0011] "Generative AI" is artificial intelligence that analyzes the content of web pages and evaluates the accuracy of their terminology and the reliability of their sources.

[0012] "Credibility" is the measure of whether information is accurate and trustworthy.

[0013] The "trustworthiness score" is a numerical representation of the trustworthiness of a web page calculated by the generating AI.

[0014] The "rating message" is a text that indicates a brief rating based on the reliability score.

[0015] A "terminal" is a device that displays search results and reliability ratings to a user, such as a PC or smartphone. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0038] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server.

[0039] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0040] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0041] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0042] The server then adds these credibility scores and rating messages to the search results, i.e., the server attaches credibility rating information to each item in the search result list that is displayed to the user.

[0043] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility score and rating message for each web page. For example, the user's device may display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list.

[0044] This allows users to easily check the reliability of web pages, and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] A user enters a search query into a search engine.

[0048] The user enters search keywords into the search box on the device and clicks the search button.

[0049] Step 2:

[0050] A server receives a search query.

[0051] The server receives a search query sent from a user's terminal.

[0052] Step 3:

[0053] The server generates a list of related web pages.

[0054] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0055] Step 4:

[0056] The server retrieves the content of each web page.

[0057] The server accesses each web page based on the generated list and retrieves its HTML content.

[0058] Step 5:

[0059] The server sends the contents of the web page to the generation AI.

[0060] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0061] Step 6:

[0062] Generative AI analyzes the content of web pages.

[0063] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0064] Step 7:

[0065] The server calculates a reliability score based on the analysis results.

[0066] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0067] Step 8:

[0068] The server generates a reliability score and a reputation message.

[0069] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0070] Step 9:

[0071] The server adds the authority rating to the search results.

[0072] The server adds the generated confidence score and rating message to each item in the search result list.

[0073] Step 10:

[0074] The device displays the search results, including the trustworthiness rating.

[0075] The user's terminal renders and displays to the user the search results including the credibility ratings sent from the server.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] The Internet contains a vast amount of information, including both accurate and reliable information and erroneous or unreliable information. Therefore, it is difficult for ordinary users to quickly find accurate and reliable information. It is particularly difficult for non-experts searching for information on a specific topic to determine its reliability. The present invention solves this problem by providing a method for evaluating the reliability of web pages and easily finding reliable information when users use search engines to obtain information.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for a terminal to send the input search query to the server; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to convert the content of the web page into analyzable data; a means for the server to analyze the content of the web page using a generative AI model and evaluate its reliability; a means for the generative AI model to generate a reliability score and an evaluation message; a means for the server to calculate a reliability score for each web page based on the analysis result; a means for the server to add the reliability score and the evaluation message to the search result; and a means for the terminal to display the search result including the reliability evaluation to the user. This allows the user to easily check the reliability of each web page in the search result and quickly find accurate and reliable information.

[0081] "User" means a public user who uses the System to enter search queries and retrieve information.

[0082] A "terminal" is an information processing device or communication device used by a user, such as a personal computer or smartphone.

[0083] "Server" means the computer system responsible for receiving the search query, generating a list of relevant web pages, analyzing the data, and calculating and assigning an authority score.

[0084] A "search query" is a keyword or phrase that a user enters into a search engine.

[0085] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze input data and generate a reliability score or evaluation message.

[0086] A "web page" is a document or piece of information that is publicly available on the Internet.

[0087] A "list" is a collection of related items or URLs.

[0088] "Analyzable data" refers to data that has been converted on a server into a format that allows the content of a web page to be sent to a generative AI model.

[0089] A "trust score" is a numerical evaluation of the trustworthiness of a web page and its content, and is a score that indicates the level of trustworthiness.

[0090] A "rating message" is a brief statement about the trustworthiness of a web page based on its trustworthiness score.

[0091] "Search Results" refers to the list of relevant web pages and their summaries that a user receives based on a search query.

[0092] The present invention is a system that evaluates the reliability of information when a user retrieves it using a search engine and provides it to the user. The system is implemented by a server, a terminal, and a user working together.

[0093] First, a user accesses a search engine through a web browser on their device, enters specific keywords, and performs a search. For example, the user enters a search query such as "benefits of health foods" and clicks the search button. This search query is sent from the device to the server. The device can be a general personal computer or a smartphone.

[0094] The server then receives the user's search query and generates a list of relevant web pages from the Internet based on the query. During this process, the server uses web scraping technology to collect the URLs of multiple relevant web pages and their summaries. The server is best served by a high-performance computer (e.g., an AWS EC2 instance).

[0095] The content of the retrieved web page is difficult to analyze as is, so it is converted into text data that can be analyzed by the server. Specifically, the HTML code of the web page is converted into text data and then formatted into an analytical data format such as JSON. This conversion process makes the content of the web page easier to handle.

[0096] The generated text data is sent from the server to a generative AI model. A large-scale natural language processing model such as GPT-4 is used as the generative AI model. This model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. As a result, it assigns a reliability score ranging from 0 to 100 to each web page and simultaneously generates an evaluation message.

[0097] For example, if the generative AI model evaluates a page as having a credibility score of 80, that information is returned to the server, which then adds these scores and a message to a search result list, ready to be presented to the user. The list includes the URL, summary, credibility score, and rating message for each web page.

[0098] Finally, the terminal displays the search result list received from the server to the user. The user can view the search result list and check the reliability score and rating message of each web page. This allows the user to easily select reliable information and access accurate information.

[0099] Examples of prompt sentences include the following:

[0100] "Please search for and evaluate reliable information about the effects of health foods."

[0101] "Search for and evaluate reliable information related to 'COVID-19 vaccine effectiveness.'"

[0102] Through this system, users can quickly obtain accurate and reliable information, reducing the risk of being misled by incorrect information.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] A user enters a specific keyword into the input field of a search engine and clicks the search button. For example, the user enters "effects of health foods" and clicks the search button. At this time, the user operates the device. The input is the search query "effects of health foods." As an output, the search query is passed to the next process.

[0106] Step 2:

[0107] The device sends the search query entered by the user to the server as an HTTP request. For example, a request in the form of a URL such as http: / / example.com / search?q=effects of health foods is sent. The input is the user's search query, and the output is a request URL that is sent to the server.

[0108] Step 3:

[0109] Based on the search query received by the server, a list of relevant web pages on the Internet is generated. The server uses web scraping technology to collect the URLs and summaries of multiple web pages related to the "benefits of health foods." The input is the search query, and the output is a list of relevant web pages (URLs and summaries). The server uses, for example, Python's BeautifulSoup library to scrape the web pages.

[0110] Step 4:

[0111] The server converts the collected web page content into parseable text data. Specifically, it converts the web page's HTML code into text data and formats it into JSON format. The input is the web page's HTML data, and the output is text data in a parseable format (such as JSON). The server extracts the text data using, for example, regular expressions (Regex) or an HTML parser.

[0112] Step 5:

[0113] The server sends the converted text data to the generative AI model, generating and sending JSON data such as the following:

[0114] {

[0115] "url": "http: / / example.com / article1",

[0116] "content": "Healthy foods have health benefits..."

[0117] }

[0118] The input is parseable text data, and the output is generated data that is sent to the generative AI model in the form of an API request.

[0119] Step 6:

[0120] The generative AI model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. Based on the evaluation, it generates a reliability score (ranging from 0 to 100) and a rating message for each web page. For example, the result might be "This page has a reliability score of 80." The input is the submitted text data, and the output is a reliability score and a rating message.

[0121] Step 7:

[0122] The server takes the reliability score and evaluation message received from the generation AI model and adds them to the search result list. For example, data in the following format is generated on the server.

[0123] {

[0124] "url": "http: / / example.com / article1",

[0125] "content": "Health foods have positive health benefits.",

[0126] "trust_score": 80,

[0127] "evaluation_message": "This page is trustworthy."

[0128] }

[0129] The input is the reliability score and evaluation message from the generative AI model, and the output is a search result list containing reliability evaluation information.

[0130] Step 8:

[0131] The device displays a search result list to the user, including the credibility ratings received from the server. The user can check the credibility score and rating message for each web page. For example, the following message appears on the user's device:

[0132] "Search results for the effects of health foods"

[0133] 1. URL: http: / / example.com / article1

[0134] Reliability score: 80

[0135] Rating message: This page is reliable.

[0136] The input is a search result list including confidence ratings, and the output is the search results that are visually displayed to the user.

[0137] (Application example 1)

[0138] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0139] In modern electronic payment services, much information and transactions are conducted online, raising concerns about fraud and fraudulent information. However, current search engines lack the functionality to evaluate the reliability of search results, which can lead to users questioning the reliability of the results. The present invention aims to provide a system that evaluates the reliability of information obtained by search engines and provides electronic payment services that users can use with confidence.

[0140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0141] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to search results; a means for the terminal to display search results including the reliability evaluation to the user; and a means for displaying the search results including the reliability evaluation in association with an electronic payment service. This allows the user to easily check the reliability of search results and use electronic payment services with peace of mind.

[0142] A "search engine" is a system that allows users to search for information on the Internet.

[0143] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0144] A "server" is a computer system that processes user requests and provides the required data.

[0145] A "web page" is a collection of documents or information that is publicly available on the Internet.

[0146] A list is an ordered arrangement of things or information.

[0147] "Generative AI" refers to technology that uses artificial intelligence to analyze data and generate information.

[0148] "Content" refers to the information contained in a sentence or description.

[0149] "Analysis" is the act of examining data or information in detail to clarify its structure and meaning.

[0150] "Credibility" is an attribute that indicates how trustworthy information or data is.

[0151] "Evaluation" is the act of judging the value or quality of an object.

[0152] A "trustworthiness score" is a numerical representation of the reliability of information or data, and serves as a standard for evaluating reliability.

[0153] "Search results" are lists of related information that are displayed when a user enters a search query.

[0154] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[0155] "Display" means to visually output information on a screen or display.

[0156] An "electronic payment service" is a system for conducting financial transactions over the Internet.

[0157] "Association" refers to linking multiple pieces of information or data based on some criteria.

[0158] The following describes an embodiment of the present invention. The present invention includes a system in which a user, a server, and a terminal cooperate to operate. To make it easier to understand the overall flow of the system, the specific operations at each step will be clarified.

[0159] The operation of the system is as follows.

[0160] First, a user enters a specific search query into a search engine. For example, let's say this query is "benefits of health foods." The user's device then sends this search query to the server, which communicates to the system the user's request for information.

[0161] Next, the server receives the search query submitted by the user and searches for relevant web pages based on it. The server generates a list of relevant web pages from the Internet and obtains the URL and summary of each web page. At this stage, no detailed analysis of the web page content is performed.

[0162] The server sends the content of each retrieved web page to the generation AI. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. An example of the use of generative AI is OpenAI's GPT-3 model. The generation AI generates a credibility score for each web page based on the analysis results. This credibility score is quantified (for example, on a scale from 0 to 100) and serves as a measure of trustworthiness. The server also generates a concise evaluation message based on the analysis results from the generation AI. An example message could be, "This page has a credibility score of 80."

[0163] The server then adds these credibility scores and rating messages to the search result list, thereby presenting each web page's credibility information along with the search results. Specifically, the server adds a credibility score and rating message to each item in the search result list displayed to the user.

[0164] Finally, the terminal displays the search results, including the credibility rating, to the user. The user can view the search results and check the credibility score and rating message of each web page. This system allows the user to easily determine the credibility of each web page and quickly and accurately select reliable information. Furthermore, by linking this credibility rating to electronic payment services, the user can make payments with peace of mind while checking the reliability of the transaction information.

[0165] For example, if a user enters the search query "cashback campaign," the system evaluates the reliability of the corresponding campaign site and identifies whether it is a fraudulent site. This reliability evaluation is achieved by having the server analyze the content of the campaign site using a generative AI model, calculating a reliability score, and visually displaying it to the user.

[0166] Below is an example of a prompt sentence to input to the generative AI model.

[0167] "Please rate the reliability of the following text:\n\n{text content}"

[0168] This allows users to use electronic payment services with peace of mind, while checking the reliability of transaction information, without worrying about fraud or fraudulent information.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] A user inputs a search query into a search engine. For example, the user inputs a search query such as "effects of health foods" and clicks the search button. At this stage, the user's input is sent to the system. The input is the search query "effects of health foods," and the output is the transmission of the query information to the server.

[0172] Step 2:

[0173] The terminal sends the user's search query to the server. The terminal sends the search query entered by the user to the server as a request. The input is the user's search query, and the output is a request sent to the server.

[0174] Step 3:

[0175] The server generates a list of relevant web pages based on the user's search query. The server searches the Internet for multiple web pages related to healthy foods and obtains their URLs and summaries. The input is the user's search query, and the output is a list of relevant web pages.

[0176] Step 4:

[0177] The server sends the content of the retrieved web pages to the generation AI to evaluate their credibility. The server then sends the text content of the retrieved web pages to the generation AI for analysis. The generation AI analyzes the accuracy of terminology and the reliability of the information source. The input is the text content of the web pages, and the output is the credibility evaluation result for each web page.

[0178] Step 5:

[0179] The server calculates the reliability score of each web page based on the evaluation results of the generation AI. The server quantifies the reliability score of each web page based on the evaluation results provided by the generation AI. The reliability score is expressed in a range from 0 to 100. The input is the evaluation result of the generation AI, and the output is the reliability score.

[0180] Step 6:

[0181] The server adds a credibility score to the search results. The server assigns a credibility score and a rating message to each item in the search result list. The input is the credibility score and rating message, and the output is a search result list with the credibility rating information added.

[0182] Step 7:

[0183] The terminal displays the search results including the trustworthiness ratings to the user. The terminal visually displays the search result list including the trustworthiness ratings received from the server to the user. The input is the search result list with the trustworthiness ratings, and the output is the search result display to the user.

[0184] Step 8:

[0185] The server associates the trustworthiness rating with the electronic payment service and displays it. The server integrates the trustworthiness score and the rating message with the information of the electronic payment service involved with the user, allowing the user to confirm the trustworthiness of the transaction information. The input is search result information with the trustworthiness rating, and the output is electronic payment service information including the trustworthiness rating.

[0186] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0187] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use a search engine to obtain information. In particular, the system has the function of recognizing users' emotions and customizing search results based on those emotions. A specific embodiment of the system is described below.

[0188] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server, and the emotion engine simultaneously analyzes the user's emotions.

[0189] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0190] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0191] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0192] The emotion engine then sends the results of the user's emotion analysis to the server, which then adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, the server can prioritize results with a high reliability score.

[0193] The server adds these reliability scores and rating messages to the search results. That is, the server adds reliability rating information to each item in the search result list displayed to the user. Furthermore, the server can visually highlight rating messages based on the analysis results of the emotion engine.

[0194] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility scores and rating messages for each web page. For example, the user's device will display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list. Furthermore, important rating messages are highlighted based on the user's sentiment.

[0195] This allows users to easily verify the reliability of web pages and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet. In addition, by providing search results customized according to the user's emotions, it is possible to provide more relevant information.

[0196] The processing flow will be explained below.

[0197] Step 1:

[0198] A user enters a search query into a search engine.

[0199] The user enters search keywords into the search box on the device and clicks the search button.

[0200] Step 2:

[0201] The emotion engine analyzes the user's emotions.

[0202] The device uses an emotion engine to analyze the user's emotions based on their facial expressions and input methods.

[0203] Step 3:

[0204] The device sends the search query and sentiment analysis results to the server.

[0205] The device sends the user's search query and sentiment analysis results together to the server.

[0206] Step 4:

[0207] The server generates a list of related web pages.

[0208] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0209] Step 5:

[0210] The server retrieves the content of each web page.

[0211] The server accesses each web page based on the generated list and retrieves its HTML content.

[0212] Step 6:

[0213] The server sends the contents of the web page to the generation AI.

[0214] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0215] Step 7:

[0216] Generative AI analyzes the content of web pages.

[0217] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0218] Step 8:

[0219] The server calculates a reliability score based on the analysis results.

[0220] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0221] Step 9:

[0222] The server generates a reliability score and a reputation message.

[0223] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0224] Step 10:

[0225] The server adjusts the trustworthiness rating based on the emotion engine's analysis results.

[0226] The server takes into account the results of the user's sentiment analysis and adjusts the display to prioritize results with high reliability scores.

[0227] Step 11:

[0228] The server adds the authority rating to the search results.

[0229] The server adds the generated confidence score and rating message to each item in the search result list.

[0230] Step 12:

[0231] The device displays the search results, including the trustworthiness rating.

[0232] The user's device renders and displays the search results including the reliability ratings sent from the server to the user, and further highlights important rating messages based on the user's sentiment.

[0233] Example 2

[0234] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] Conventional search engines provide information based on search queries entered by users, but because they lack a means to evaluate the reliability of that information, it can contain inaccurate or unreliable information. Furthermore, because they provide uniform search results without taking into account the user's emotional state, it is difficult for the user to properly understand and interpret the information, which presents a challenge.

[0236] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input a search query to a search engine; a means for a terminal to transmit the search query and emotion data to the server; a means for the server to generate a list of related information based on the user's search query; a means for transmitting the content of web pages acquired by the server to a generation AI for analysis; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the emotion engine to transmit the results obtained by analyzing the user's emotions to the server; a means for the server to adjust the reliability evaluation based on the emotion analysis results; a means for adding the adjusted reliability score to the search results; and a means for the terminal to display search results including the reliability evaluation to the user. This allows the user to easily select reliable information and obtain appropriate search results according to the user's emotional state.

[0237] "User" refers to a person who uses the system to search for information.

[0238] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0239] "Terminal" refers to an electronic device used by a user to enter a search query.

[0240] "Server" refers to a central computer system that processes search queries received from users and provides relevant information.

[0241] "Emotion data" refers to data that represents the user's emotional state.

[0242] "Related information list" refers to a list of related web pages or documents generated by a server based on a search query.

[0243] "Generative AI" refers to artificial intelligence that analyzes incoming text and data and assesses its reliability.

[0244] The "trustworthiness score" is a numerical representation of the reliability of a web page or piece of information calculated by the generating AI based on the analysis results.

[0245] An "emotion engine" refers to a system that analyzes a user's emotions and generates the results.

[0246] "Reliability assessment" is a collective term for the analysis results and reliability score performed by the generative AI.

[0247] "Search results" refers to a list of relevant information provided to a user by a server, including an authority rating.

[0248] "Rating Message" refers to a brief description or message based on the credibility score.

[0249] MODE FOR CARRYING OUT THE INVENTION

[0250] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system is particularly equipped with a function to recognize users' emotions and customize search results based on those emotions.

[0251] First, a user enters a specific keyword into a search engine and performs a search. For example, the user enters "effects of health foods" and presses the search button. At this stage, the user's device sends the search query to the server. At the same time, the device uses an emotion engine to analyze the user's emotion data and also sends it to the server.

[0252] The server retrieves a list of relevant information from the Internet based on the received search query. For example, this includes the URLs of multiple web pages related to health foods and their summaries. The server then sends the content of each retrieved web page to the generation AI for analysis. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. For example, if the generation AI determines that a web page is based on a reliable source, it assigns the web page a high reliability score.

[0253] The analysis results are sent from the AI ​​generator to the server, which then calculates a credibility score for each web page based on the results. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, the message might say, "This page has a credibility score of 80."

[0254] The emotion engine then analyzes the user's emotional data and sends it to the server. The server receives the emotion analysis results and adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, it can prioritize results with a high reliability score.

[0255] Finally, the server adds these reliability scores and rating messages to the search results and sends the adjusted search results to the user's device. The device displays the search results, including the received reliability ratings, to the user. The user can view the search results and check the reliability scores and rating messages of each web page. For example, the user's device may display a "reliability score of 80" for each item in the "Search results for the effects of health foods" list. In addition, important rating messages may be highlighted based on the user's sentiment.

[0256] As a concrete example, consider a scenario in which a user searches for "benefits of health foods" and emotional data indicating "the user is currently in an anxious state" is sent to the server. The server retrieves the relevant webpage and requests analysis from the generation AI. The generation AI analyzes the webpage and generates an evaluation of "trust score 80." The emotion engine then analyzes the user's state of anxiety again and sends the result to the server. The server adjusts the display to prioritize highly reliable information for users in an anxious state. As a result, the webpage with a "trust score of 80" is displayed on the user's device.

[0257] An example of a prompt sentence might be:

[0258] "There is so much information about the effects of health foods that I'm confused. Please tell me some reliable information."

[0259] "I'd like to research the effects of health foods, but I'm not sure which information is accurate. Please give me some guidelines."

[0260] Through this system, users can not only quickly obtain reliable information, but also obtain appropriate search results according to their emotional state.

[0261] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0262] Specific explanation of processing steps

[0263] Step 1:

[0264] A user inputs a search query. For example, the user inputs the keyword "effects of health foods" into a search engine and executes a search. This input operation generates a search query.

[0265] Step 2:

[0266] The device sends the search query and emotion data to the server. The device sends the entered search query to the server, and also analyzes the user's emotion using an emotion engine and sends the data. For example, the query "Effects of health foods" and the emotion data "The user is currently feeling anxious" are sent to the server.

[0267] Step 3:

[0268] The server generates a list of relevant information based on the search query. The server searches the received search query using databases and Internet sources to generate a list of relevant web pages and documents, including URLs and summaries. For example, a list of web pages related to healthy foods is generated.

[0269] Step 4:

[0270] The server sends the retrieved webpage content to the generation AI for analysis. The server then sends the text content of the relevant webpage to the generation AI, which evaluates the accuracy of the terminology and the reliability of the source. The generation AI analyzes the received text data and performs a reliability evaluation. For example, the generation AI analyzes the content of the webpage and generates data such as "terminology accuracy 90%; source reliability 85%."

[0271] Step 5:

[0272] The server calculates a reliability score for each web page based on the analysis results. Based on the evaluation data received from the generation AI, the server calculates a reliability score for each web page. The reliability score is quantified on a scale from 0 to 100. For example, a "reliability score of 80" is calculated by combining the accuracy of the terminology and the reliability of the source of information.

[0273] Step 6:

[0274] The emotion engine analyzes the user's emotions and sends the results to the server. The emotion engine analyzes the user's emotions again and provides the results to the server. For example, the analysis result "The user is still in an anxious state" is sent to the server.

[0275] Step 7:

[0276] The server adjusts the reliability rating based on the results of emotion analysis. The server adjusts the reliability score taking into account the results of emotion analysis. If the user is expressing anxiety, the server adjusts the display so that information with a high reliability score is given priority. For example, a rule such as "for users in an anxious state, information with a reliability score of 85 or higher is given priority" is applied.

[0277] Step 8:

[0278] The server adds the adjusted credibility score and rating message to each search result item, and presents them in a user-friendly format, such as "Credit score 80" or "This page provides reliable information."

[0279] Step 9:

[0280] The terminal displays the search results to the user. The terminal displays the search results, including the reliability rating received from the server, to the user. The user can check the reliability score and rating message for each web page. For example, a list of "search results related to the effects of health foods" will display a "reliability score of 80."

[0281] This allows users to easily find reliable information and obtain appropriate search results according to their emotional state.

[0282] (Application example 2)

[0283] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] There is a huge amount of information on the Internet, and when users use search engines to retrieve information, it is extremely difficult to determine whether the information is reliable. Furthermore, because the ability to judge the reliability of information varies from user to user depending on their emotional and psychological state, there is a high risk of being misled by incorrect information. Therefore, there is a need for a system that allows users to quickly access more reliable information according to their emotional state.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0286] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to the search results; and a means for the terminal to display the search results including the reliability evaluation to the user and highlight them based on the user's emotions. This makes it possible to quickly provide reliable information customized according to the user's emotions.

[0287] A "search engine" is a program that searches the Internet for information based on a user-entered query and generates a list of relevant web pages.

[0288] "Generative AI" is an artificial intelligence technology that analyzes the content of web pages and evaluates their reliability.

[0289] The "trustworthiness score" is a numerical representation of the trustworthiness of a web page, and is a value evaluated by the generating AI.

[0290] "Highlighting based on emotion" is a function that analyzes the user's emotional state and displays search results in a visually striking way according to that emotion.

[0291] A "rating message" is a brief statement about the trustworthiness of a web page that is generated based on the trustworthiness score.

[0292] A "server" is a network device that receives a user's search query, generates a list of relevant web pages, and uses generation AI to obtain analysis results.

[0293] A "terminal" is an electronic device that allows a user to receive and display search results.

[0294] This invention provides a system that evaluates the reliability of information when a user retrieves information using a search engine, and customizes and displays search results based on the user's sentiment. The system includes a server, a user terminal, and several software modules.

[0295] First, a user uses their device to enter a specific keyword into a search engine. For example, they enter a keyword such as "latest security threats." This information is sent from the user's device to the server, and at the same time, an emotion engine implemented on the device analyzes the user's emotions. This emotion engine uses a library called EmotionAnalyzer.

[0296] The server then generates a list of relevant web pages based on the received search query. The server retrieves relevant web pages from the Internet using a library such as requests and prepares their content for analysis.

[0297] The server then analyzes the content of each web page using a generative AI model. This analysis evaluates the accuracy of the terminology contained in the web page and the trustworthiness of the source. Using a generative AI model library, the server generates an evaluation result and a credibility score. For example, if a web page is determined to be based on a credible source, the page is assigned a high credibility score.

[0298] Once the credibility scores and rating messages are generated, the server uses them to create a list of search results, adding a credibility score to each item. User sentiment analysis is also taken into account at this stage, and web pages with high credibility ratings are customised to be highlighted.

[0299] Finally, the user's device displays these customized search results. The user can see the credibility score and rating message for each web page. For example, if a user comments, "I'm very worried after reading the news recently," the results that are highly credible will be highlighted.

[0300] For example, the following prompt sentences are used:

[0301] "Show me an article about the latest security threats. I'm very worried about what I've read in the news lately."

[0302] This system allows users to easily find reliable information and quickly obtain appropriate information that matches their individual emotions.

[0303] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0304] Step 1:

[0305] A user enters keywords into a search engine on their device. This information is sent from the user's device to the server, and at the same time, an emotion engine on the device analyzes the user's emotions. Specifically, a user enters the search keywords "latest security threats" and comments "I feel very anxious after reading the recent news." This comment is input into the EmotionAnalyzer library, which analyzes the user's emotions. The inputs are "search keywords" and "user comments," and the output is "the user's emotional state."

[0306] Step 2:

[0307] The server searches for relevant web pages based on the search query it receives. The server uses the requests library to retrieve information from the Internet. For example, the server retrieves URLs and page contents related to "latest security threats." The input is the "search query" and the output is a "list of relevant web pages."

[0308] Step 3:

[0309] The server uses a generative AI model to analyze the content of retrieved web pages and evaluate their reliability. The generative AI model analyzes the text of each web page and evaluates the accuracy of the terminology and the reliability of the source of information. The input is a list of web pages, and the output is a reliability score and evaluation message for each web page. Specifically, the generative AI model scans the page content and uses an AI algorithm to evaluate the appropriateness of the terminology.

[0310] Step 4:

[0311] Based on the evaluation results obtained from the generative AI model, the server calculates a reliability score for each web page and generates a concise evaluation message. At the same time, it customizes the search result list according to the user's emotional state. Pages with high reliability scores are displayed preferentially. The input is a "reliability score and evaluation message," and the output is a "customized search result list." Specifically, if the user expresses anxiety, pages with high reliability scores are arranged at the top of the search results.

[0312] Step 5:

[0313] The device receives the customized search result list sent from the server and displays it to the user. The user can check the reliability scores and rating messages and select the most appropriate information. The input is the "customized search result list" and the output is the "result list displayed to the user." In concrete terms, the device visually presents the highly reliable results highlighted.

[0314] Through these processing steps, users can quickly obtain reliable information that is optimally tailored to their emotional state. For example, if a user inputs the prompt, "Show me articles about the latest security threats. I'm very anxious after reading the recent news," the system will detect the user's anxiety and highlight and display reliable security information.

[0315] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0316] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0317] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0318] [Second embodiment]

[0319] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0320] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0321] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0322] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0323] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0324] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0325] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0326] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0327] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0328] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0329] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0330] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0331] The present invention is a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0332] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server.

[0333] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0334] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0335] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0336] The server then adds these credibility scores and rating messages to the search results, i.e., the server attaches credibility rating information to each item in the search result list that is displayed to the user.

[0337] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility score and rating message for each web page. For example, the user's device may display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list.

[0338] This allows users to easily check the reliability of web pages, and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet.

[0339] The processing flow will be explained below.

[0340] Step 1:

[0341] A user enters a search query into a search engine.

[0342] The user enters search keywords into the search box on the device and clicks the search button.

[0343] Step 2:

[0344] A server receives a search query.

[0345] The server receives a search query sent from a user's terminal.

[0346] Step 3:

[0347] The server generates a list of related web pages.

[0348] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0349] Step 4:

[0350] The server retrieves the content of each web page.

[0351] The server accesses each web page based on the generated list and retrieves its HTML content.

[0352] Step 5:

[0353] The server sends the contents of the web page to the generation AI.

[0354] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0355] Step 6:

[0356] Generative AI analyzes the content of web pages.

[0357] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0358] Step 7:

[0359] The server calculates a reliability score based on the analysis results.

[0360] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0361] Step 8:

[0362] The server generates a reliability score and a reputation message.

[0363] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0364] Step 9:

[0365] The server adds the authority rating to the search results.

[0366] The server adds the generated confidence score and rating message to each item in the search result list.

[0367] Step 10:

[0368] The device displays the search results, including the trustworthiness rating.

[0369] The user's terminal renders and displays to the user the search results including the credibility ratings sent from the server.

[0370] Example 1

[0371] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0372] The Internet contains a vast amount of information, including both accurate and reliable information and erroneous or unreliable information. Therefore, it is difficult for ordinary users to quickly find accurate and reliable information. It is particularly difficult for non-experts searching for information on a specific topic to determine its reliability. The present invention solves this problem by providing a method for evaluating the reliability of web pages and easily finding reliable information when users use search engines to obtain information.

[0373] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0374] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for a terminal to send the input search query to the server; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to convert the content of the web page into analyzable data; a means for the server to analyze the content of the web page using a generative AI model and evaluate its reliability; a means for the generative AI model to generate a reliability score and an evaluation message; a means for the server to calculate a reliability score for each web page based on the analysis result; a means for the server to add the reliability score and the evaluation message to the search result; and a means for the terminal to display the search result including the reliability evaluation to the user. This allows the user to easily check the reliability of each web page in the search result and quickly find accurate and reliable information.

[0375] "User" means a public user who uses the System to enter search queries and retrieve information.

[0376] A "terminal" is an information processing device or communication device used by a user, such as a personal computer or smartphone.

[0377] "Server" means the computer system responsible for receiving the search query, generating a list of relevant web pages, analyzing the data, and calculating and assigning an authority score.

[0378] A "search query" is a keyword or phrase that a user enters into a search engine.

[0379] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze input data and generate a reliability score or evaluation message.

[0380] A "web page" is a document or piece of information that is publicly available on the Internet.

[0381] A "list" is a collection of related items or URLs.

[0382] "Analyzable data" refers to data that has been converted on a server into a format that allows the content of a web page to be sent to a generative AI model.

[0383] A "trust score" is a numerical evaluation of the trustworthiness of a web page and its content, and is a score that indicates the level of trustworthiness.

[0384] A "rating message" is a brief statement about the trustworthiness of a web page based on its trustworthiness score.

[0385] "Search Results" refers to the list of relevant web pages and their summaries that a user receives based on a search query.

[0386] The present invention is a system that evaluates the reliability of information when a user retrieves it using a search engine and provides it to the user. The system is implemented by a server, a terminal, and a user working together.

[0387] First, a user accesses a search engine through a web browser on their device, enters specific keywords, and performs a search. For example, the user enters a search query such as "benefits of health foods" and clicks the search button. This search query is sent from the device to the server. The device can be a general personal computer or a smartphone.

[0388] The server then receives the user's search query and generates a list of relevant web pages from the Internet based on the query. During this process, the server uses web scraping technology to collect the URLs of multiple relevant web pages and their summaries. The server is best served by a high-performance computer (e.g., an AWS EC2 instance).

[0389] The content of the retrieved web page is difficult to analyze as is, so it is converted into text data that can be analyzed by the server. Specifically, the HTML code of the web page is converted into text data and then formatted into an analytical data format such as JSON. This conversion process makes the content of the web page easier to handle.

[0390] The generated text data is sent from the server to a generative AI model. A large-scale natural language processing model such as GPT-4 is used as the generative AI model. This model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. As a result, it assigns a reliability score ranging from 0 to 100 to each web page and simultaneously generates an evaluation message.

[0391] For example, if the generative AI model evaluates a page as having a credibility score of 80, that information is returned to the server, which then adds these scores and a message to a search result list, ready to be presented to the user. The list includes the URL, summary, credibility score, and rating message for each web page.

[0392] Finally, the terminal displays the search result list received from the server to the user. The user can view the search result list and check the reliability score and rating message of each web page. This allows the user to easily select reliable information and access accurate information.

[0393] Examples of prompt sentences include the following:

[0394] "Please search for and evaluate reliable information about the effects of health foods."

[0395] "Search for and evaluate reliable information related to 'COVID-19 vaccine effectiveness.'"

[0396] Through this system, users can quickly obtain accurate and reliable information, reducing the risk of being misled by incorrect information.

[0397] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0398] Step 1:

[0399] A user enters a specific keyword into the input field of a search engine and clicks the search button. For example, the user enters "effects of health foods" and clicks the search button. At this time, the user operates the device. The input is the search query "effects of health foods." As an output, the search query is passed to the next process.

[0400] Step 2:

[0401] The device sends the search query entered by the user to the server as an HTTP request. For example, a request in the form of a URL such as http: / / example.com / search?q=effects of health foods is sent. The input is the user's search query, and the output is a request URL that is sent to the server.

[0402] Step 3:

[0403] Based on the search query received by the server, a list of relevant web pages on the Internet is generated. The server uses web scraping technology to collect the URLs and summaries of multiple web pages related to the "benefits of health foods." The input is the search query, and the output is a list of relevant web pages (URLs and summaries). The server uses, for example, Python's BeautifulSoup library to scrape the web pages.

[0404] Step 4:

[0405] The server converts the collected web page content into parseable text data. Specifically, it converts the web page's HTML code into text data and formats it into JSON format. The input is the web page's HTML data, and the output is text data in a parseable format (such as JSON). The server extracts the text data using, for example, regular expressions (Regex) or an HTML parser.

[0406] Step 5:

[0407] The server sends the converted text data to the generative AI model, generating and sending JSON data such as the following:

[0408] {

[0409] "url": "http: / / example.com / article1",

[0410] "content": "Healthy foods have health benefits..."

[0411] }

[0412] The input is parseable text data, and the output is generated data that is sent to the generative AI model in the form of an API request.

[0413] Step 6:

[0414] The generative AI model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. Based on the evaluation, it generates a reliability score (ranging from 0 to 100) and a rating message for each web page. For example, the result might be "This page has a reliability score of 80." The input is the submitted text data, and the output is a reliability score and a rating message.

[0415] Step 7:

[0416] The server takes the reliability score and evaluation message received from the generation AI model and adds them to the search result list. For example, data in the following format is generated on the server.

[0417] {

[0418] "url": "http: / / example.com / article1",

[0419] "content": "Health foods have positive health benefits.",

[0420] "trust_score": 80,

[0421] "evaluation_message": "This page is trustworthy."

[0422] }

[0423] The input is the reliability score and evaluation message from the generative AI model, and the output is a search result list containing reliability evaluation information.

[0424] Step 8:

[0425] The device displays a search result list to the user, including the credibility ratings received from the server. The user can check the credibility score and rating message for each web page. For example, the following message appears on the user's device:

[0426] "Search results for the effects of health foods"

[0427] 1. URL: http: / / example.com / article1

[0428] Reliability score: 80

[0429] Rating message: This page is reliable.

[0430] The input is a search result list including confidence ratings, and the output is the search results that are visually displayed to the user.

[0431] (Application example 1)

[0432] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] In modern electronic payment services, much information and transactions are conducted online, raising concerns about fraud and fraudulent information. However, current search engines lack the functionality to evaluate the reliability of search results, which can lead to users questioning the reliability of the results. The present invention aims to provide a system that evaluates the reliability of information obtained by search engines and provides electronic payment services that users can use with confidence.

[0434] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0435] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to search results; a means for the terminal to display search results including the reliability evaluation to the user; and a means for displaying the search results including the reliability evaluation in association with an electronic payment service. This allows the user to easily check the reliability of search results and use electronic payment services with peace of mind.

[0436] A "search engine" is a system that allows users to search for information on the Internet.

[0437] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0438] A "server" is a computer system that processes user requests and provides the required data.

[0439] A "web page" is a collection of documents or information that is publicly available on the Internet.

[0440] A list is an ordered arrangement of things or information.

[0441] "Generative AI" refers to technology that uses artificial intelligence to analyze data and generate information.

[0442] "Content" refers to the information contained in a sentence or description.

[0443] "Analysis" is the act of examining data or information in detail to clarify its structure and meaning.

[0444] "Credibility" is an attribute that indicates how trustworthy information or data is.

[0445] "Evaluation" is the act of judging the value or quality of an object.

[0446] A "trustworthiness score" is a numerical representation of the reliability of information or data, and serves as a standard for evaluating reliability.

[0447] "Search results" are lists of related information that are displayed when a user enters a search query.

[0448] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[0449] "Display" means to visually output information on a screen or display.

[0450] An "electronic payment service" is a system for conducting financial transactions over the Internet.

[0451] "Association" refers to linking multiple pieces of information or data based on some criteria.

[0452] The following describes an embodiment of the present invention. The present invention includes a system in which a user, a server, and a terminal cooperate to operate. To make it easier to understand the overall flow of the system, the specific operations at each step will be clarified.

[0453] The operation of the system is as follows.

[0454] First, a user enters a specific search query into a search engine. For example, let's say this query is "benefits of health foods." The user's device then sends this search query to the server, which communicates to the system the user's request for information.

[0455] Next, the server receives the search query submitted by the user and searches for relevant web pages based on it. The server generates a list of relevant web pages from the Internet and obtains the URL and summary of each web page. At this stage, no detailed analysis of the web page content is performed.

[0456] The server sends the content of each retrieved web page to the generation AI. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. An example of the use of generative AI is OpenAI's GPT-3 model. The generation AI generates a credibility score for each web page based on the analysis results. This credibility score is quantified (for example, on a scale from 0 to 100) and serves as a measure of trustworthiness. The server also generates a concise evaluation message based on the analysis results from the generation AI. An example message could be, "This page has a credibility score of 80."

[0457] The server then adds these credibility scores and rating messages to the search result list, thereby presenting each web page's credibility information along with the search results. Specifically, the server adds a credibility score and rating message to each item in the search result list displayed to the user.

[0458] Finally, the terminal displays the search results, including the credibility rating, to the user. The user can view the search results and check the credibility score and rating message of each web page. This system allows the user to easily determine the credibility of each web page and quickly and accurately select reliable information. Furthermore, by linking this credibility rating to electronic payment services, the user can make payments with peace of mind while checking the reliability of the transaction information.

[0459] For example, if a user enters the search query "cashback campaign," the system evaluates the reliability of the corresponding campaign site and identifies whether it is a fraudulent site. This reliability evaluation is achieved by having the server analyze the content of the campaign site using a generative AI model, calculating a reliability score, and visually displaying it to the user.

[0460] Below is an example of a prompt sentence to input to the generative AI model.

[0461] "Please rate the reliability of the following text:\n\n{text content}"

[0462] This allows users to use electronic payment services with peace of mind, while checking the reliability of transaction information, without worrying about fraud or fraudulent information.

[0463] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0464] Step 1:

[0465] A user inputs a search query into a search engine. For example, the user inputs a search query such as "effects of health foods" and clicks the search button. At this stage, the user's input is sent to the system. The input is the search query "effects of health foods," and the output is the transmission of the query information to the server.

[0466] Step 2:

[0467] The terminal sends the user's search query to the server. The terminal sends the search query entered by the user to the server as a request. The input is the user's search query, and the output is a request sent to the server.

[0468] Step 3:

[0469] The server generates a list of relevant web pages based on the user's search query. The server searches the Internet for multiple web pages related to healthy foods and obtains their URLs and summaries. The input is the user's search query, and the output is a list of relevant web pages.

[0470] Step 4:

[0471] The server sends the content of the retrieved web pages to the generation AI to evaluate their credibility. The server then sends the text content of the retrieved web pages to the generation AI for analysis. The generation AI analyzes the accuracy of terminology and the reliability of the information source. The input is the text content of the web pages, and the output is the credibility evaluation result for each web page.

[0472] Step 5:

[0473] The server calculates the reliability score of each web page based on the evaluation results of the generation AI. The server quantifies the reliability score of each web page based on the evaluation results provided by the generation AI. The reliability score is expressed in a range from 0 to 100. The input is the evaluation result of the generation AI, and the output is the reliability score.

[0474] Step 6:

[0475] The server adds a credibility score to the search results. The server assigns a credibility score and a rating message to each item in the search result list. The input is the credibility score and rating message, and the output is a search result list with the credibility rating information added.

[0476] Step 7:

[0477] The terminal displays the search results including the trustworthiness ratings to the user. The terminal visually displays the search result list including the trustworthiness ratings received from the server to the user. The input is the search result list with the trustworthiness ratings, and the output is the search result display to the user.

[0478] Step 8:

[0479] The server associates the trustworthiness rating with the electronic payment service and displays it. The server integrates the trustworthiness score and the rating message with the information of the electronic payment service involved with the user, allowing the user to confirm the trustworthiness of the transaction information. The input is search result information with the trustworthiness rating, and the output is electronic payment service information including the trustworthiness rating.

[0480] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0481] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use a search engine to obtain information. In particular, the system has the function of recognizing users' emotions and customizing search results based on those emotions. A specific embodiment of the system is described below.

[0482] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server, and the emotion engine simultaneously analyzes the user's emotions.

[0483] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0484] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0485] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0486] The emotion engine then sends the results of the user's emotion analysis to the server, which then adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, the server can prioritize results with a high reliability score.

[0487] The server adds these reliability scores and rating messages to the search results. That is, the server adds reliability rating information to each item in the search result list displayed to the user. Furthermore, the server can visually highlight rating messages based on the analysis results of the emotion engine.

[0488] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility scores and rating messages for each web page. For example, the user's device will display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list. Furthermore, important rating messages are highlighted based on the user's sentiment.

[0489] This allows users to easily verify the reliability of web pages and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet. In addition, by providing search results customized according to the user's emotions, it is possible to provide more relevant information.

[0490] The processing flow will be explained below.

[0491] Step 1:

[0492] A user enters a search query into a search engine.

[0493] The user enters search keywords into the search box on the device and clicks the search button.

[0494] Step 2:

[0495] The emotion engine analyzes the user's emotions.

[0496] The device uses an emotion engine to analyze the user's emotions based on their facial expressions and input methods.

[0497] Step 3:

[0498] The device sends the search query and sentiment analysis results to the server.

[0499] The device sends the user's search query and sentiment analysis results together to the server.

[0500] Step 4:

[0501] The server generates a list of related web pages.

[0502] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0503] Step 5:

[0504] The server retrieves the content of each web page.

[0505] The server accesses each web page based on the generated list and retrieves its HTML content.

[0506] Step 6:

[0507] The server sends the contents of the web page to the generation AI.

[0508] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0509] Step 7:

[0510] Generative AI analyzes the content of web pages.

[0511] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0512] Step 8:

[0513] The server calculates a reliability score based on the analysis results.

[0514] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0515] Step 9:

[0516] The server generates a reliability score and a reputation message.

[0517] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0518] Step 10:

[0519] The server adjusts the trustworthiness rating based on the emotion engine's analysis results.

[0520] The server takes into account the results of the user's sentiment analysis and adjusts the display to prioritize results with high reliability scores.

[0521] Step 11:

[0522] The server adds the authority rating to the search results.

[0523] The server adds the generated confidence score and rating message to each item in the search result list.

[0524] Step 12:

[0525] The device displays the search results, including the trustworthiness rating.

[0526] The user's device renders and displays the search results including the reliability ratings sent from the server to the user, and further highlights important rating messages based on the user's sentiment.

[0527] Example 2

[0528] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0529] Conventional search engines provide information based on search queries entered by users, but because they lack a means to evaluate the reliability of that information, it can contain inaccurate or unreliable information. Furthermore, because they provide uniform search results without taking into account the user's emotional state, it is difficult for the user to properly understand and interpret the information, which presents a challenge.

[0530] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input a search query to a search engine; a means for a terminal to transmit the search query and emotion data to the server; a means for the server to generate a list of related information based on the user's search query; a means for transmitting the content of web pages acquired by the server to a generation AI for analysis; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the emotion engine to transmit the results obtained by analyzing the user's emotions to the server; a means for the server to adjust the reliability evaluation based on the emotion analysis results; a means for adding the adjusted reliability score to the search results; and a means for the terminal to display search results including the reliability evaluation to the user. This allows the user to easily select reliable information and obtain appropriate search results according to the user's emotional state.

[0531] "User" refers to a person who uses the system to search for information.

[0532] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0533] "Terminal" refers to an electronic device used by a user to enter a search query.

[0534] "Server" refers to a central computer system that processes search queries received from users and provides relevant information.

[0535] "Emotion data" refers to data that represents the user's emotional state.

[0536] "Related information list" refers to a list of related web pages or documents generated by a server based on a search query.

[0537] "Generative AI" refers to artificial intelligence that analyzes incoming text and data and assesses its reliability.

[0538] The "trustworthiness score" is a numerical representation of the reliability of a web page or piece of information calculated by the generating AI based on the analysis results.

[0539] An "emotion engine" refers to a system that analyzes a user's emotions and generates the results.

[0540] "Reliability assessment" is a collective term for the analysis results and reliability score performed by the generative AI.

[0541] "Search results" refers to a list of relevant information provided to a user by a server, including an authority rating.

[0542] "Rating Message" refers to a brief description or message based on the credibility score.

[0543] MODE FOR CARRYING OUT THE INVENTION

[0544] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system is particularly equipped with a function to recognize users' emotions and customize search results based on those emotions.

[0545] First, a user enters a specific keyword into a search engine and performs a search. For example, the user enters "effects of health foods" and presses the search button. At this stage, the user's device sends the search query to the server. At the same time, the device uses an emotion engine to analyze the user's emotion data and also sends it to the server.

[0546] The server retrieves a list of relevant information from the Internet based on the received search query. For example, this includes the URLs of multiple web pages related to health foods and their summaries. The server then sends the content of each retrieved web page to the generation AI for analysis. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. For example, if the generation AI determines that a web page is based on a reliable source, it assigns the web page a high reliability score.

[0547] The analysis results are sent from the AI ​​generator to the server, which then calculates a credibility score for each web page based on the results. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, the message might say, "This page has a credibility score of 80."

[0548] The emotion engine then analyzes the user's emotional data and sends it to the server. The server receives the emotion analysis results and adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, it can prioritize results with a high reliability score.

[0549] Finally, the server adds these reliability scores and rating messages to the search results and sends the adjusted search results to the user's device. The device displays the search results, including the received reliability ratings, to the user. The user can view the search results and check the reliability scores and rating messages of each web page. For example, the user's device may display a "reliability score of 80" for each item in the "Search results for the effects of health foods" list. In addition, important rating messages may be highlighted based on the user's sentiment.

[0550] As a concrete example, consider a scenario in which a user searches for "benefits of health foods" and emotional data indicating "the user is currently in an anxious state" is sent to the server. The server retrieves the relevant webpage and requests analysis from the generation AI. The generation AI analyzes the webpage and generates an evaluation of "trust score 80." The emotion engine then analyzes the user's state of anxiety again and sends the result to the server. The server adjusts the display to prioritize highly reliable information for users in an anxious state. As a result, the webpage with a "trust score of 80" is displayed on the user's device.

[0551] An example of a prompt sentence might be:

[0552] "There is so much information about the effects of health foods that I'm confused. Please tell me some reliable information."

[0553] "I'd like to research the effects of health foods, but I'm not sure which information is accurate. Please give me some guidelines."

[0554] Through this system, users can not only quickly obtain reliable information, but also obtain appropriate search results according to their emotional state.

[0555] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0556] Specific explanation of processing steps

[0557] Step 1:

[0558] A user inputs a search query. For example, the user inputs the keyword "effects of health foods" into a search engine and executes a search. This input operation generates a search query.

[0559] Step 2:

[0560] The device sends the search query and emotion data to the server. The device sends the entered search query to the server, and also analyzes the user's emotion using an emotion engine and sends the data. For example, the query "Effects of health foods" and the emotion data "The user is currently feeling anxious" are sent to the server.

[0561] Step 3:

[0562] The server generates a list of relevant information based on the search query. The server searches the received search query using databases and Internet sources to generate a list of relevant web pages and documents, including URLs and summaries. For example, a list of web pages related to healthy foods is generated.

[0563] Step 4:

[0564] The server sends the retrieved webpage content to the generation AI for analysis. The server then sends the text content of the relevant webpage to the generation AI, which evaluates the accuracy of the terminology and the reliability of the source. The generation AI analyzes the received text data and performs a reliability evaluation. For example, the generation AI analyzes the content of the webpage and generates data such as "terminology accuracy 90%; source reliability 85%."

[0565] Step 5:

[0566] The server calculates a reliability score for each web page based on the analysis results. Based on the evaluation data received from the generation AI, the server calculates a reliability score for each web page. The reliability score is quantified on a scale from 0 to 100. For example, a "reliability score of 80" is calculated by combining the accuracy of the terminology and the reliability of the source of information.

[0567] Step 6:

[0568] The emotion engine analyzes the user's emotions and sends the results to the server. The emotion engine analyzes the user's emotions again and provides the results to the server. For example, the analysis result "The user is still in an anxious state" is sent to the server.

[0569] Step 7:

[0570] The server adjusts the reliability rating based on the results of emotion analysis. The server adjusts the reliability score taking into account the results of emotion analysis. If the user is expressing anxiety, the server adjusts the display so that information with a high reliability score is given priority. For example, a rule such as "for users in an anxious state, information with a reliability score of 85 or higher is given priority" is applied.

[0571] Step 8:

[0572] The server adds the adjusted credibility score and rating message to each search result item, and presents them in a user-friendly format, such as "Credit score 80" or "This page provides reliable information."

[0573] Step 9:

[0574] The terminal displays the search results to the user. The terminal displays the search results, including the reliability rating received from the server, to the user. The user can check the reliability score and rating message for each web page. For example, a list of "search results related to the effects of health foods" will display a "reliability score of 80."

[0575] This allows users to easily find reliable information and obtain appropriate search results according to their emotional state.

[0576] (Application example 2)

[0577] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0578] There is a huge amount of information on the Internet, and when users use search engines to retrieve information, it is extremely difficult to determine whether the information is reliable. Furthermore, because the ability to judge the reliability of information varies from user to user depending on their emotional and psychological state, there is a high risk of being misled by incorrect information. Therefore, there is a need for a system that allows users to quickly access more reliable information according to their emotional state.

[0579] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0580] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to the search results; and a means for the terminal to display the search results including the reliability evaluation to the user and highlight them based on the user's emotions. This makes it possible to quickly provide reliable information customized according to the user's emotions.

[0581] A "search engine" is a program that searches the Internet for information based on a user-entered query and generates a list of relevant web pages.

[0582] "Generative AI" is an artificial intelligence technology that analyzes the content of web pages and evaluates their reliability.

[0583] The "trustworthiness score" is a numerical representation of the trustworthiness of a web page, and is a value evaluated by the generating AI.

[0584] "Highlighting based on emotion" is a function that analyzes the user's emotional state and displays search results in a visually striking way according to that emotion.

[0585] A "rating message" is a brief statement about the trustworthiness of a web page that is generated based on the trustworthiness score.

[0586] A "server" is a network device that receives a user's search query, generates a list of relevant web pages, and uses generation AI to obtain analysis results.

[0587] A "terminal" is an electronic device that allows a user to receive and display search results.

[0588] This invention provides a system that evaluates the reliability of information when a user retrieves information using a search engine, and customizes and displays search results based on the user's sentiment. The system includes a server, a user terminal, and several software modules.

[0589] First, a user uses their device to enter a specific keyword into a search engine. For example, they enter a keyword such as "latest security threats." This information is sent from the user's device to the server, and at the same time, an emotion engine implemented on the device analyzes the user's emotions. This emotion engine uses a library called EmotionAnalyzer.

[0590] The server then generates a list of relevant web pages based on the received search query. The server retrieves relevant web pages from the Internet using a library such as requests and prepares their content for analysis.

[0591] The server then analyzes the content of each web page using a generative AI model. This analysis evaluates the accuracy of the terminology contained in the web page and the trustworthiness of the source. Using a generative AI model library, the server generates an evaluation result and a credibility score. For example, if a web page is determined to be based on a credible source, the page is assigned a high credibility score.

[0592] Once the credibility scores and rating messages are generated, the server uses them to create a list of search results, adding a credibility score to each item. User sentiment analysis is also taken into account at this stage, and web pages with high credibility ratings are customised to be highlighted.

[0593] Finally, the user's device displays these customized search results. The user can see the credibility score and rating message for each web page. For example, if a user comments, "I'm very worried after reading the news recently," the results that are highly credible will be highlighted.

[0594] For example, the following prompt sentences are used:

[0595] "Show me an article about the latest security threats. I'm very worried about what I've read in the news lately."

[0596] This system allows users to easily find reliable information and quickly obtain appropriate information that matches their individual emotions.

[0597] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0598] Step 1:

[0599] A user enters keywords into a search engine on their device. This information is sent from the user's device to the server, and at the same time, an emotion engine on the device analyzes the user's emotions. Specifically, a user enters the search keywords "latest security threats" and comments "I feel very anxious after reading the recent news." This comment is input into the EmotionAnalyzer library, which analyzes the user's emotions. The inputs are "search keywords" and "user comments," and the output is "the user's emotional state."

[0600] Step 2:

[0601] The server searches for relevant web pages based on the search query it receives. The server uses the requests library to retrieve information from the Internet. For example, the server retrieves URLs and page contents related to "latest security threats." The input is the "search query" and the output is a "list of relevant web pages."

[0602] Step 3:

[0603] The server uses a generative AI model to analyze the content of retrieved web pages and evaluate their reliability. The generative AI model analyzes the text of each web page and evaluates the accuracy of the terminology and the reliability of the source of information. The input is a list of web pages, and the output is a reliability score and evaluation message for each web page. Specifically, the generative AI model scans the page content and uses an AI algorithm to evaluate the appropriateness of the terminology.

[0604] Step 4:

[0605] Based on the evaluation results obtained from the generative AI model, the server calculates a reliability score for each web page and generates a concise evaluation message. At the same time, it customizes the search result list according to the user's emotional state. Pages with high reliability scores are displayed preferentially. The input is a "reliability score and evaluation message," and the output is a "customized search result list." Specifically, if the user expresses anxiety, pages with high reliability scores are arranged at the top of the search results.

[0606] Step 5:

[0607] The device receives the customized search result list sent from the server and displays it to the user. The user can check the reliability scores and rating messages and select the most appropriate information. The input is the "customized search result list" and the output is the "result list displayed to the user." In concrete terms, the device visually presents the highly reliable results highlighted.

[0608] Through these processing steps, users can quickly obtain reliable information that is optimally tailored to their emotional state. For example, if a user inputs the prompt, "Show me articles about the latest security threats. I'm very anxious after reading the recent news," the system will detect the user's anxiety and highlight and display reliable security information.

[0609] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0610] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0611] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0612] [Third embodiment]

[0613] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0614] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0615] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0616] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0617] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0618] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0619] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0620] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0621] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0622] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0623] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0624] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0625] The present invention is a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0626] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server.

[0627] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0628] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0629] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0630] The server then adds these credibility scores and rating messages to the search results, i.e., the server attaches credibility rating information to each item in the search result list that is displayed to the user.

[0631] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility score and rating message for each web page. For example, the user's device may display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list.

[0632] This allows users to easily check the reliability of web pages, and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet.

[0633] The processing flow will be explained below.

[0634] Step 1:

[0635] A user enters a search query into a search engine.

[0636] The user enters search keywords into the search box on the device and clicks the search button.

[0637] Step 2:

[0638] A server receives a search query.

[0639] The server receives a search query sent from a user's terminal.

[0640] Step 3:

[0641] The server generates a list of related web pages.

[0642] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0643] Step 4:

[0644] The server retrieves the content of each web page.

[0645] The server accesses each web page based on the generated list and retrieves its HTML content.

[0646] Step 5:

[0647] The server sends the contents of the web page to the generation AI.

[0648] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0649] Step 6:

[0650] Generative AI analyzes the content of web pages.

[0651] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0652] Step 7:

[0653] The server calculates a reliability score based on the analysis results.

[0654] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0655] Step 8:

[0656] The server generates a reliability score and a reputation message.

[0657] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0658] Step 9:

[0659] The server adds the authority rating to the search results.

[0660] The server adds the generated confidence score and rating message to each item in the search result list.

[0661] Step 10:

[0662] The device displays the search results, including the trustworthiness rating.

[0663] The user's terminal renders and displays to the user the search results including the credibility ratings sent from the server.

[0664] Example 1

[0665] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0666] The Internet contains a vast amount of information, including both accurate and reliable information and erroneous or unreliable information. Therefore, it is difficult for ordinary users to quickly find accurate and reliable information. It is particularly difficult for non-experts searching for information on a specific topic to determine its reliability. The present invention solves this problem by providing a method for evaluating the reliability of web pages and easily finding reliable information when users use search engines to obtain information.

[0667] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0668] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for a terminal to send the input search query to the server; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to convert the content of the web page into analyzable data; a means for the server to analyze the content of the web page using a generative AI model and evaluate its reliability; a means for the generative AI model to generate a reliability score and an evaluation message; a means for the server to calculate a reliability score for each web page based on the analysis result; a means for the server to add the reliability score and the evaluation message to the search result; and a means for the terminal to display the search result including the reliability evaluation to the user. This allows the user to easily check the reliability of each web page in the search result and quickly find accurate and reliable information.

[0669] "User" means a public user who uses the System to enter search queries and retrieve information.

[0670] A "terminal" is an information processing device or communication device used by a user, such as a personal computer or smartphone.

[0671] "Server" means the computer system responsible for receiving the search query, generating a list of relevant web pages, analyzing the data, and calculating and assigning an authority score.

[0672] A "search query" is a keyword or phrase that a user enters into a search engine.

[0673] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze input data and generate a reliability score or evaluation message.

[0674] A "web page" is a document or piece of information that is publicly available on the Internet.

[0675] A "list" is a collection of related items or URLs.

[0676] "Analyzable data" refers to data that has been converted on a server into a format that allows the content of a web page to be sent to a generative AI model.

[0677] A "trust score" is a numerical evaluation of the trustworthiness of a web page and its content, and is a score that indicates the level of trustworthiness.

[0678] A "rating message" is a brief statement about the trustworthiness of a web page based on its trustworthiness score.

[0679] "Search Results" refers to the list of relevant web pages and their summaries that a user receives based on a search query.

[0680] The present invention is a system that evaluates the reliability of information when a user retrieves it using a search engine and provides it to the user. The system is implemented by a server, a terminal, and a user working together.

[0681] First, a user accesses a search engine through a web browser on their device, enters specific keywords, and performs a search. For example, the user enters a search query such as "benefits of health foods" and clicks the search button. This search query is sent from the device to the server. The device can be a general personal computer or a smartphone.

[0682] The server then receives the user's search query and generates a list of relevant web pages from the Internet based on the query. During this process, the server uses web scraping technology to collect the URLs of multiple relevant web pages and their summaries. The server is best served by a high-performance computer (e.g., an AWS EC2 instance).

[0683] The content of the retrieved web page is difficult to analyze as is, so it is converted into text data that can be analyzed by the server. Specifically, the HTML code of the web page is converted into text data and then formatted into an analytical data format such as JSON. This conversion process makes the content of the web page easier to handle.

[0684] The generated text data is sent from the server to a generative AI model. A large-scale natural language processing model such as GPT-4 is used as the generative AI model. This model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. As a result, it assigns a reliability score ranging from 0 to 100 to each web page and simultaneously generates an evaluation message.

[0685] For example, if the generative AI model evaluates a page as having a credibility score of 80, that information is returned to the server, which then adds these scores and a message to a search result list, ready to be presented to the user. The list includes the URL, summary, credibility score, and rating message for each web page.

[0686] Finally, the terminal displays the search result list received from the server to the user. The user can view the search result list and check the reliability score and rating message of each web page. This allows the user to easily select reliable information and access accurate information.

[0687] Examples of prompt sentences include the following:

[0688] "Please search for and evaluate reliable information about the effects of health foods."

[0689] "Search for and evaluate reliable information related to 'COVID-19 vaccine effectiveness.'"

[0690] Through this system, users can quickly obtain accurate and reliable information, reducing the risk of being misled by incorrect information.

[0691] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0692] Step 1:

[0693] A user enters a specific keyword into the input field of a search engine and clicks the search button. For example, the user enters "effects of health foods" and clicks the search button. At this time, the user operates the device. The input is the search query "effects of health foods." As an output, the search query is passed to the next process.

[0694] Step 2:

[0695] The device sends the search query entered by the user to the server as an HTTP request. For example, a request in the form of a URL such as http: / / example.com / search?q=effects of health foods is sent. The input is the user's search query, and the output is a request URL that is sent to the server.

[0696] Step 3:

[0697] Based on the search query received by the server, a list of relevant web pages on the Internet is generated. The server uses web scraping technology to collect the URLs and summaries of multiple web pages related to the "benefits of health foods." The input is the search query, and the output is a list of relevant web pages (URLs and summaries). The server uses, for example, Python's BeautifulSoup library to scrape the web pages.

[0698] Step 4:

[0699] The server converts the collected web page content into parseable text data. Specifically, it converts the web page's HTML code into text data and formats it into JSON format. The input is the web page's HTML data, and the output is text data in a parseable format (such as JSON). The server extracts the text data using, for example, regular expressions (Regex) or an HTML parser.

[0700] Step 5:

[0701] The server sends the converted text data to the generative AI model, generating and sending JSON data such as the following:

[0702] {

[0703] "url": "http: / / example.com / article1",

[0704] "content": "Healthy foods have health benefits..."

[0705] }

[0706] The input is parseable text data, and the output is generated data that is sent to the generative AI model in the form of an API request.

[0707] Step 6:

[0708] The generative AI model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. Based on the evaluation, it generates a reliability score (ranging from 0 to 100) and a rating message for each web page. For example, the result might be "This page has a reliability score of 80." The input is the submitted text data, and the output is a reliability score and a rating message.

[0709] Step 7:

[0710] The server takes the reliability score and evaluation message received from the generation AI model and adds them to the search result list. For example, data in the following format is generated on the server.

[0711] {

[0712] "url": "http: / / example.com / article1",

[0713] "content": "Health foods have positive health benefits.",

[0714] "trust_score": 80,

[0715] "evaluation_message": "This page is trustworthy."

[0716] }

[0717] The input is the reliability score and evaluation message from the generative AI model, and the output is a search result list containing reliability evaluation information.

[0718] Step 8:

[0719] The device displays a search result list to the user, including the credibility ratings received from the server. The user can check the credibility score and rating message for each web page. For example, the following message appears on the user's device:

[0720] "Search results for the effects of health foods"

[0721] 1. URL: http: / / example.com / article1

[0722] Reliability score: 80

[0723] Rating message: This page is reliable.

[0724] The input is a search result list including confidence ratings, and the output is the search results that are visually displayed to the user.

[0725] (Application example 1)

[0726] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0727] In modern electronic payment services, much information and transactions are conducted online, raising concerns about fraud and fraudulent information. However, current search engines lack the functionality to evaluate the reliability of search results, which can lead to users questioning the reliability of the results. The present invention aims to provide a system that evaluates the reliability of information obtained by search engines and provides electronic payment services that users can use with confidence.

[0728] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0729] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to search results; a means for the terminal to display search results including the reliability evaluation to the user; and a means for displaying the search results including the reliability evaluation in association with an electronic payment service. This allows the user to easily check the reliability of search results and use electronic payment services with peace of mind.

[0730] A "search engine" is a system that allows users to search for information on the Internet.

[0731] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0732] A "server" is a computer system that processes user requests and provides the required data.

[0733] A "web page" is a collection of documents or information that is publicly available on the Internet.

[0734] A list is an ordered arrangement of things or information.

[0735] "Generative AI" refers to technology that uses artificial intelligence to analyze data and generate information.

[0736] "Content" refers to the information contained in a sentence or description.

[0737] "Analysis" is the act of examining data or information in detail to clarify its structure and meaning.

[0738] "Credibility" is an attribute that indicates how trustworthy information or data is.

[0739] "Evaluation" is the act of judging the value or quality of an object.

[0740] A "trustworthiness score" is a numerical representation of the reliability of information or data, and serves as a standard for evaluating reliability.

[0741] "Search results" are lists of related information that are displayed when a user enters a search query.

[0742] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[0743] "Display" means to visually output information on a screen or display.

[0744] An "electronic payment service" is a system for conducting financial transactions over the Internet.

[0745] "Association" refers to linking multiple pieces of information or data based on some criteria.

[0746] The following describes an embodiment of the present invention. The present invention includes a system in which a user, a server, and a terminal cooperate to operate. To make it easier to understand the overall flow of the system, the specific operations at each step will be clarified.

[0747] The operation of the system is as follows.

[0748] First, a user enters a specific search query into a search engine. For example, let's say this query is "benefits of health foods." The user's device then sends this search query to the server, which communicates to the system the user's request for information.

[0749] Next, the server receives the search query submitted by the user and searches for relevant web pages based on it. The server generates a list of relevant web pages from the Internet and obtains the URL and summary of each web page. At this stage, no detailed analysis of the web page content is performed.

[0750] The server sends the content of each retrieved web page to the generation AI. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. An example of the use of generative AI is OpenAI's GPT-3 model. The generation AI generates a credibility score for each web page based on the analysis results. This credibility score is quantified (for example, on a scale from 0 to 100) and serves as a measure of trustworthiness. The server also generates a concise evaluation message based on the analysis results from the generation AI. An example message could be, "This page has a credibility score of 80."

[0751] The server then adds these credibility scores and rating messages to the search result list, thereby presenting each web page's credibility information along with the search results. Specifically, the server adds a credibility score and rating message to each item in the search result list displayed to the user.

[0752] Finally, the terminal displays the search results, including the credibility rating, to the user. The user can view the search results and check the credibility score and rating message of each web page. This system allows the user to easily determine the credibility of each web page and quickly and accurately select reliable information. Furthermore, by linking this credibility rating to electronic payment services, the user can make payments with peace of mind while checking the reliability of the transaction information.

[0753] For example, if a user enters the search query "cashback campaign," the system evaluates the reliability of the corresponding campaign site and identifies whether it is a fraudulent site. This reliability evaluation is achieved by having the server analyze the content of the campaign site using a generative AI model, calculating a reliability score, and visually displaying it to the user.

[0754] Below is an example of a prompt sentence to input to the generative AI model.

[0755] "Please rate the reliability of the following text:\n\n{text content}"

[0756] This allows users to use electronic payment services with peace of mind, while checking the reliability of transaction information, without worrying about fraud or fraudulent information.

[0757] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0758] Step 1:

[0759] A user inputs a search query into a search engine. For example, the user inputs a search query such as "effects of health foods" and clicks the search button. At this stage, the user's input is sent to the system. The input is the search query "effects of health foods," and the output is the transmission of the query information to the server.

[0760] Step 2:

[0761] The terminal sends the user's search query to the server. The terminal sends the search query entered by the user to the server as a request. The input is the user's search query, and the output is a request sent to the server.

[0762] Step 3:

[0763] The server generates a list of relevant web pages based on the user's search query. The server searches the Internet for multiple web pages related to healthy foods and obtains their URLs and summaries. The input is the user's search query, and the output is a list of relevant web pages.

[0764] Step 4:

[0765] The server sends the content of the retrieved web pages to the generation AI to evaluate their credibility. The server then sends the text content of the retrieved web pages to the generation AI for analysis. The generation AI analyzes the accuracy of terminology and the reliability of the information source. The input is the text content of the web pages, and the output is the credibility evaluation result for each web page.

[0766] Step 5:

[0767] The server calculates the reliability score of each web page based on the evaluation results of the generation AI. The server quantifies the reliability score of each web page based on the evaluation results provided by the generation AI. The reliability score is expressed in a range from 0 to 100. The input is the evaluation result of the generation AI, and the output is the reliability score.

[0768] Step 6:

[0769] The server adds a credibility score to the search results. The server assigns a credibility score and a rating message to each item in the search result list. The input is the credibility score and rating message, and the output is a search result list with the credibility rating information added.

[0770] Step 7:

[0771] The terminal displays the search results including the trustworthiness ratings to the user. The terminal visually displays the search result list including the trustworthiness ratings received from the server to the user. The input is the search result list with the trustworthiness ratings, and the output is the search result display to the user.

[0772] Step 8:

[0773] The server associates the trustworthiness rating with the electronic payment service and displays it. The server integrates the trustworthiness score and the rating message with the information of the electronic payment service involved with the user, allowing the user to confirm the trustworthiness of the transaction information. The input is search result information with the trustworthiness rating, and the output is electronic payment service information including the trustworthiness rating.

[0774] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0775] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use a search engine to obtain information. In particular, the system has the function of recognizing users' emotions and customizing search results based on those emotions. A specific embodiment of the system is described below.

[0776] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server, and the emotion engine simultaneously analyzes the user's emotions.

[0777] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0778] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0779] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0780] The emotion engine then sends the results of the user's emotion analysis to the server, which then adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, the server can prioritize results with a high reliability score.

[0781] The server adds these reliability scores and rating messages to the search results. That is, the server adds reliability rating information to each item in the search result list displayed to the user. Furthermore, the server can visually highlight rating messages based on the analysis results of the emotion engine.

[0782] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility scores and rating messages for each web page. For example, the user's device will display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list. Furthermore, important rating messages are highlighted based on the user's sentiment.

[0783] This allows users to easily verify the reliability of web pages and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet. In addition, by providing search results customized according to the user's emotions, it is possible to provide more relevant information.

[0784] The processing flow will be explained below.

[0785] Step 1:

[0786] A user enters a search query into a search engine.

[0787] The user enters search keywords into the search box on the device and clicks the search button.

[0788] Step 2:

[0789] The emotion engine analyzes the user's emotions.

[0790] The device uses an emotion engine to analyze the user's emotions based on their facial expressions and input methods.

[0791] Step 3:

[0792] The device sends the search query and sentiment analysis results to the server.

[0793] The device sends the user's search query and sentiment analysis results together to the server.

[0794] Step 4:

[0795] The server generates a list of related web pages.

[0796] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0797] Step 5:

[0798] The server retrieves the content of each web page.

[0799] The server accesses each web page based on the generated list and retrieves its HTML content.

[0800] Step 6:

[0801] The server sends the contents of the web page to the generation AI.

[0802] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0803] Step 7:

[0804] Generative AI analyzes the content of web pages.

[0805] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0806] Step 8:

[0807] The server calculates a reliability score based on the analysis results.

[0808] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0809] Step 9:

[0810] The server generates a reliability score and a reputation message.

[0811] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0812] Step 10:

[0813] The server adjusts the trustworthiness rating based on the emotion engine's analysis results.

[0814] The server takes into account the results of the user's sentiment analysis and adjusts the display to prioritize results with high reliability scores.

[0815] Step 11:

[0816] The server adds the authority rating to the search results.

[0817] The server adds the generated confidence score and rating message to each item in the search result list.

[0818] Step 12:

[0819] The device displays the search results, including the trustworthiness rating.

[0820] The user's device renders and displays the search results including the reliability ratings sent from the server to the user, and further highlights important rating messages based on the user's sentiment.

[0821] Example 2

[0822] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0823] Conventional search engines provide information based on search queries entered by users, but because they lack a means to evaluate the reliability of that information, it can contain inaccurate or unreliable information. Furthermore, because they provide uniform search results without taking into account the user's emotional state, it is difficult for the user to properly understand and interpret the information, which presents a challenge.

[0824] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input a search query to a search engine; a means for a terminal to transmit the search query and emotion data to the server; a means for the server to generate a list of related information based on the user's search query; a means for transmitting the content of web pages acquired by the server to a generation AI for analysis; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the emotion engine to transmit the results obtained by analyzing the user's emotions to the server; a means for the server to adjust the reliability evaluation based on the emotion analysis results; a means for adding the adjusted reliability score to the search results; and a means for the terminal to display search results including the reliability evaluation to the user. This allows the user to easily select reliable information and obtain appropriate search results according to the user's emotional state.

[0825] "User" refers to a person who uses the system to search for information.

[0826] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[0827] "Terminal" refers to an electronic device used by a user to enter a search query.

[0828] "Server" refers to a central computer system that processes search queries received from users and provides relevant information.

[0829] "Emotion data" refers to data that represents the user's emotional state.

[0830] "Related information list" refers to a list of related web pages or documents generated by a server based on a search query.

[0831] "Generative AI" refers to artificial intelligence that analyzes incoming text and data and assesses its reliability.

[0832] The "trustworthiness score" is a numerical representation of the reliability of a web page or piece of information calculated by the generating AI based on the analysis results.

[0833] An "emotion engine" refers to a system that analyzes a user's emotions and generates the results.

[0834] "Reliability assessment" is a collective term for the analysis results and reliability score performed by the generative AI.

[0835] "Search results" refers to a list of relevant information provided to a user by a server, including an authority rating.

[0836] "Rating Message" refers to a brief description or message based on the credibility score.

[0837] MODE FOR CARRYING OUT THE INVENTION

[0838] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system is particularly equipped with a function to recognize users' emotions and customize search results based on those emotions.

[0839] First, a user enters a specific keyword into a search engine and performs a search. For example, the user enters "effects of health foods" and presses the search button. At this stage, the user's device sends the search query to the server. At the same time, the device uses an emotion engine to analyze the user's emotion data and also sends it to the server.

[0840] The server retrieves a list of relevant information from the Internet based on the received search query. For example, this includes the URLs of multiple web pages related to health foods and their summaries. The server then sends the content of each retrieved web page to the generation AI for analysis. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. For example, if the generation AI determines that a web page is based on a reliable source, it assigns the web page a high reliability score.

[0841] The analysis results are sent from the AI ​​generator to the server, which then calculates a credibility score for each web page based on the results. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, the message might say, "This page has a credibility score of 80."

[0842] The emotion engine then analyzes the user's emotional data and sends it to the server. The server receives the emotion analysis results and adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, it can prioritize results with a high reliability score.

[0843] Finally, the server adds these reliability scores and rating messages to the search results and sends the adjusted search results to the user's device. The device displays the search results, including the received reliability ratings, to the user. The user can view the search results and check the reliability scores and rating messages of each web page. For example, the user's device may display a "reliability score of 80" for each item in the "Search results for the effects of health foods" list. In addition, important rating messages may be highlighted based on the user's sentiment.

[0844] As a concrete example, consider a scenario in which a user searches for "benefits of health foods" and emotional data indicating "the user is currently in an anxious state" is sent to the server. The server retrieves the relevant webpage and requests analysis from the generation AI. The generation AI analyzes the webpage and generates an evaluation of "trust score 80." The emotion engine then analyzes the user's state of anxiety again and sends the result to the server. The server adjusts the display to prioritize highly reliable information for users in an anxious state. As a result, the webpage with a "trust score of 80" is displayed on the user's device.

[0845] An example of a prompt sentence might be:

[0846] "There is so much information about the effects of health foods that I'm confused. Please tell me some reliable information."

[0847] "I'd like to research the effects of health foods, but I'm not sure which information is accurate. Please give me some guidelines."

[0848] Through this system, users can not only quickly obtain reliable information, but also obtain appropriate search results according to their emotional state.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] Specific explanation of processing steps

[0851] Step 1:

[0852] A user inputs a search query. For example, the user inputs the keyword "effects of health foods" into a search engine and executes a search. This input operation generates a search query.

[0853] Step 2:

[0854] The device sends the search query and emotion data to the server. The device sends the entered search query to the server, and also analyzes the user's emotion using an emotion engine and sends the data. For example, the query "Effects of health foods" and the emotion data "The user is currently feeling anxious" are sent to the server.

[0855] Step 3:

[0856] The server generates a list of relevant information based on the search query. The server searches the received search query using databases and Internet sources to generate a list of relevant web pages and documents, including URLs and summaries. For example, a list of web pages related to healthy foods is generated.

[0857] Step 4:

[0858] The server sends the retrieved webpage content to the generation AI for analysis. The server then sends the text content of the relevant webpage to the generation AI, which evaluates the accuracy of the terminology and the reliability of the source. The generation AI analyzes the received text data and performs a reliability evaluation. For example, the generation AI analyzes the content of the webpage and generates data such as "terminology accuracy 90%; source reliability 85%."

[0859] Step 5:

[0860] The server calculates a reliability score for each web page based on the analysis results. Based on the evaluation data received from the generation AI, the server calculates a reliability score for each web page. The reliability score is quantified on a scale from 0 to 100. For example, a "reliability score of 80" is calculated by combining the accuracy of the terminology and the reliability of the source of information.

[0861] Step 6:

[0862] The emotion engine analyzes the user's emotions and sends the results to the server. The emotion engine analyzes the user's emotions again and provides the results to the server. For example, the analysis result "The user is still in an anxious state" is sent to the server.

[0863] Step 7:

[0864] The server adjusts the reliability rating based on the results of emotion analysis. The server adjusts the reliability score taking into account the results of emotion analysis. If the user is expressing anxiety, the server adjusts the display so that information with a high reliability score is given priority. For example, a rule such as "for users in an anxious state, information with a reliability score of 85 or higher is given priority" is applied.

[0865] Step 8:

[0866] The server adds the adjusted credibility score and rating message to each search result item, and presents them in a user-friendly format, such as "Credit score 80" or "This page provides reliable information."

[0867] Step 9:

[0868] The terminal displays the search results to the user. The terminal displays the search results, including the reliability rating received from the server, to the user. The user can check the reliability score and rating message for each web page. For example, a list of "search results related to the effects of health foods" will display a "reliability score of 80."

[0869] This allows users to easily find reliable information and obtain appropriate search results according to their emotional state.

[0870] (Application example 2)

[0871] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0872] There is a huge amount of information on the Internet, and when users use search engines to retrieve information, it is extremely difficult to determine whether the information is reliable. Furthermore, because the ability to judge the reliability of information varies from user to user depending on their emotional and psychological state, there is a high risk of being misled by incorrect information. Therefore, there is a need for a system that allows users to quickly access more reliable information according to their emotional state.

[0873] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0874] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to the search results; and a means for the terminal to display the search results including the reliability evaluation to the user and highlight them based on the user's emotions. This makes it possible to quickly provide reliable information customized according to the user's emotions.

[0875] A "search engine" is a program that searches the Internet for information based on a user-entered query and generates a list of relevant web pages.

[0876] "Generative AI" is an artificial intelligence technology that analyzes the content of web pages and evaluates their reliability.

[0877] The "trustworthiness score" is a numerical representation of the trustworthiness of a web page, and is a value evaluated by the generating AI.

[0878] "Highlighting based on emotion" is a function that analyzes the user's emotional state and displays search results in a visually striking way according to that emotion.

[0879] A "rating message" is a brief statement about the trustworthiness of a web page that is generated based on the trustworthiness score.

[0880] A "server" is a network device that receives a user's search query, generates a list of relevant web pages, and uses generation AI to obtain analysis results.

[0881] A "terminal" is an electronic device that allows a user to receive and display search results.

[0882] This invention provides a system that evaluates the reliability of information when a user retrieves information using a search engine, and customizes and displays search results based on the user's sentiment. The system includes a server, a user terminal, and several software modules.

[0883] First, a user uses their device to enter a specific keyword into a search engine. For example, they enter a keyword such as "latest security threats." This information is sent from the user's device to the server, and at the same time, an emotion engine implemented on the device analyzes the user's emotions. This emotion engine uses a library called EmotionAnalyzer.

[0884] The server then generates a list of relevant web pages based on the received search query. The server retrieves relevant web pages from the Internet using a library such as requests and prepares their content for analysis.

[0885] The server then analyzes the content of each web page using a generative AI model. This analysis evaluates the accuracy of the terminology contained in the web page and the trustworthiness of the source. Using a generative AI model library, the server generates an evaluation result and a credibility score. For example, if a web page is determined to be based on a credible source, the page is assigned a high credibility score.

[0886] Once the credibility scores and rating messages are generated, the server uses them to create a list of search results, adding a credibility score to each item. User sentiment analysis is also taken into account at this stage, and web pages with high credibility ratings are customised to be highlighted.

[0887] Finally, the user's device displays these customized search results. The user can see the credibility score and rating message for each web page. For example, if a user comments, "I'm very worried after reading the news recently," the results that are highly credible will be highlighted.

[0888] For example, the following prompt sentences are used:

[0889] "Show me an article about the latest security threats. I'm very worried about what I've read in the news lately."

[0890] This system allows users to easily find reliable information and quickly obtain appropriate information that matches their individual emotions.

[0891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0892] Step 1:

[0893] A user enters keywords into a search engine on their device. This information is sent from the user's device to the server, and at the same time, an emotion engine on the device analyzes the user's emotions. Specifically, a user enters the search keywords "latest security threats" and comments "I feel very anxious after reading the recent news." This comment is input into the EmotionAnalyzer library, which analyzes the user's emotions. The inputs are "search keywords" and "user comments," and the output is "the user's emotional state."

[0894] Step 2:

[0895] The server searches for relevant web pages based on the search query it receives. The server uses the requests library to retrieve information from the Internet. For example, the server retrieves URLs and page contents related to "latest security threats." The input is the "search query" and the output is a "list of relevant web pages."

[0896] Step 3:

[0897] The server uses a generative AI model to analyze the content of retrieved web pages and evaluate their reliability. The generative AI model analyzes the text of each web page and evaluates the accuracy of the terminology and the reliability of the source of information. The input is a list of web pages, and the output is a reliability score and evaluation message for each web page. Specifically, the generative AI model scans the page content and uses an AI algorithm to evaluate the appropriateness of the terminology.

[0898] Step 4:

[0899] Based on the evaluation results obtained from the generative AI model, the server calculates a reliability score for each web page and generates a concise evaluation message. At the same time, it customizes the search result list according to the user's emotional state. Pages with high reliability scores are displayed preferentially. The input is a "reliability score and evaluation message," and the output is a "customized search result list." Specifically, if the user expresses anxiety, pages with high reliability scores are arranged at the top of the search results.

[0900] Step 5:

[0901] The device receives the customized search result list sent from the server and displays it to the user. The user can check the reliability scores and rating messages and select the most appropriate information. The input is the "customized search result list" and the output is the "result list displayed to the user." In concrete terms, the device visually presents the highly reliable results highlighted.

[0902] Through these processing steps, users can quickly obtain reliable information that is optimally tailored to their emotional state. For example, if a user inputs the prompt, "Show me articles about the latest security threats. I'm very anxious after reading the recent news," the system will detect the user's anxiety and highlight and display reliable security information.

[0903] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0904] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0905] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0906] [Fourth embodiment]

[0907] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0908] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0909] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0910] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0911] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0912] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0913] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0914] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0915] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0916] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0917] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0918] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0919] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0920] The present invention is a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0921] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server.

[0922] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[0923] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[0924] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[0925] The server then adds these credibility scores and rating messages to the search results, i.e., the server attaches credibility rating information to each item in the search result list that is displayed to the user.

[0926] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility score and rating message for each web page. For example, the user's device may display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list.

[0927] This allows users to easily check the reliability of web pages, and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] A user enters a search query into a search engine.

[0931] The user enters search keywords into the search box on the device and clicks the search button.

[0932] Step 2:

[0933] A server receives a search query.

[0934] The server receives a search query sent from a user's terminal.

[0935] Step 3:

[0936] The server generates a list of related web pages.

[0937] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[0938] Step 4:

[0939] The server retrieves the content of each web page.

[0940] The server accesses each web page based on the generated list and retrieves its HTML content.

[0941] Step 5:

[0942] The server sends the contents of the web page to the generation AI.

[0943] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[0944] Step 6:

[0945] Generative AI analyzes the content of web pages.

[0946] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[0947] Step 7:

[0948] The server calculates a reliability score based on the analysis results.

[0949] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[0950] Step 8:

[0951] The server generates a reliability score and a reputation message.

[0952] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[0953] Step 9:

[0954] The server adds the authority rating to the search results.

[0955] The server adds the generated confidence score and rating message to each item in the search result list.

[0956] Step 10:

[0957] The device displays the search results, including the trustworthiness rating.

[0958] The user's terminal renders and displays to the user the search results including the credibility ratings sent from the server.

[0959] Example 1

[0960] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0961] The Internet contains a vast amount of information, including both accurate and reliable information and erroneous or unreliable information. Therefore, it is difficult for ordinary users to quickly find accurate and reliable information. It is particularly difficult for non-experts searching for information on a specific topic to determine its reliability. The present invention solves this problem by providing a method for evaluating the reliability of web pages and easily finding reliable information when users use search engines to obtain information.

[0962] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0963] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for a terminal to send the input search query to the server; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to convert the content of the web page into analyzable data; a means for the server to analyze the content of the web page using a generative AI model and evaluate its reliability; a means for the generative AI model to generate a reliability score and an evaluation message; a means for the server to calculate a reliability score for each web page based on the analysis result; a means for the server to add the reliability score and the evaluation message to the search result; and a means for the terminal to display the search result including the reliability evaluation to the user. This allows the user to easily check the reliability of each web page in the search result and quickly find accurate and reliable information.

[0964] "User" means a public user who uses the System to enter search queries and retrieve information.

[0965] A "terminal" is an information processing device or communication device used by a user, such as a personal computer or smartphone.

[0966] "Server" means the computer system responsible for receiving the search query, generating a list of relevant web pages, analyzing the data, and calculating and assigning an authority score.

[0967] A "search query" is a keyword or phrase that a user enters into a search engine.

[0968] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to analyze input data and generate a reliability score or evaluation message.

[0969] A "web page" is a document or piece of information that is publicly available on the Internet.

[0970] A "list" is a collection of related items or URLs.

[0971] "Analyzable data" refers to data that has been converted on a server into a format that allows the content of a web page to be sent to a generative AI model.

[0972] A "trust score" is a numerical evaluation of the trustworthiness of a web page and its content, and is a score that indicates the level of trustworthiness.

[0973] A "rating message" is a brief statement about the trustworthiness of a web page based on its trustworthiness score.

[0974] "Search Results" refers to the list of relevant web pages and their summaries that a user receives based on a search query.

[0975] The present invention is a system that evaluates the reliability of information when a user retrieves it using a search engine and provides it to the user. The system is implemented by a server, a terminal, and a user working together.

[0976] First, a user accesses a search engine through a web browser on their device, enters specific keywords, and performs a search. For example, the user enters a search query such as "benefits of health foods" and clicks the search button. This search query is sent from the device to the server. The device can be a general personal computer or a smartphone.

[0977] The server then receives the user's search query and generates a list of relevant web pages from the Internet based on the query. During this process, the server uses web scraping technology to collect the URLs of multiple relevant web pages and their summaries. The server is best served by a high-performance computer (e.g., an AWS EC2 instance).

[0978] The content of the retrieved web page is difficult to analyze as is, so it is converted into text data that can be analyzed by the server. Specifically, the HTML code of the web page is converted into text data and then formatted into an analytical data format such as JSON. This conversion process makes the content of the web page easier to handle.

[0979] The generated text data is sent from the server to a generative AI model. A large-scale natural language processing model such as GPT-4 is used as the generative AI model. This model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. As a result, it assigns a reliability score ranging from 0 to 100 to each web page and simultaneously generates an evaluation message.

[0980] For example, if the generative AI model evaluates a page as having a credibility score of 80, that information is returned to the server, which then adds these scores and a message to a search result list, ready to be presented to the user. The list includes the URL, summary, credibility score, and rating message for each web page.

[0981] Finally, the terminal displays the search result list received from the server to the user. The user can view the search result list and check the reliability score and rating message of each web page. This allows the user to easily select reliable information and access accurate information.

[0982] Examples of prompt sentences include the following:

[0983] "Please search for and evaluate reliable information about the effects of health foods."

[0984] "Search for and evaluate reliable information related to 'COVID-19 vaccine effectiveness.'"

[0985] Through this system, users can quickly obtain accurate and reliable information, reducing the risk of being misled by incorrect information.

[0986] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0987] Step 1:

[0988] A user enters a specific keyword into the input field of a search engine and clicks the search button. For example, the user enters "effects of health foods" and clicks the search button. At this time, the user operates the device. The input is the search query "effects of health foods." As an output, the search query is passed to the next process.

[0989] Step 2:

[0990] The device sends the search query entered by the user to the server as an HTTP request. For example, a request in the form of a URL such as http: / / example.com / search?q=effects of health foods is sent. The input is the user's search query, and the output is a request URL that is sent to the server.

[0991] Step 3:

[0992] Based on the search query received by the server, a list of relevant web pages on the Internet is generated. The server uses web scraping technology to collect the URLs and summaries of multiple web pages related to the "benefits of health foods." The input is the search query, and the output is a list of relevant web pages (URLs and summaries). The server uses, for example, Python's BeautifulSoup library to scrape the web pages.

[0993] Step 4:

[0994] The server converts the collected web page content into parseable text data. Specifically, it converts the web page's HTML code into text data and formats it into JSON format. The input is the web page's HTML data, and the output is text data in a parseable format (such as JSON). The server extracts the text data using, for example, regular expressions (Regex) or an HTML parser.

[0995] Step 5:

[0996] The server sends the converted text data to the generative AI model, generating and sending JSON data such as the following:

[0997] {

[0998] "url": "http: / / example.com / article1",

[0999] "content": "Healthy foods have health benefits..."

[1000] }

[1001] The input is parseable text data, and the output is generated data that is sent to the generative AI model in the form of an API request.

[1002] Step 6:

[1003] The generative AI model analyzes the received text data and evaluates the accuracy of terminology and the reliability of the source. Based on the evaluation, it generates a reliability score (ranging from 0 to 100) and a rating message for each web page. For example, the result might be "This page has a reliability score of 80." The input is the submitted text data, and the output is a reliability score and a rating message.

[1004] Step 7:

[1005] The server takes the reliability score and evaluation message received from the generation AI model and adds them to the search result list. For example, data in the following format is generated on the server.

[1006] {

[1007] "url": "http: / / example.com / article1",

[1008] "content": "Health foods have positive health benefits.",

[1009] "trust_score": 80,

[1010] "evaluation_message": "This page is trustworthy."

[1011] }

[1012] The input is the reliability score and evaluation message from the generative AI model, and the output is a search result list containing reliability evaluation information.

[1013] Step 8:

[1014] The device displays a search result list to the user, including the credibility ratings received from the server. The user can check the credibility score and rating message for each web page. For example, the following message appears on the user's device:

[1015] "Search results for the effects of health foods"

[1016] 1. URL: http: / / example.com / article1

[1017] Reliability score: 80

[1018] Rating message: This page is reliable.

[1019] The input is a search result list including confidence ratings, and the output is the search results that are visually displayed to the user.

[1020] (Application example 1)

[1021] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1022] In modern electronic payment services, much information and transactions are conducted online, raising concerns about fraud and fraudulent information. However, current search engines lack the functionality to evaluate the reliability of search results, which can lead to users questioning the reliability of the results. The present invention aims to provide a system that evaluates the reliability of information obtained by search engines and provides electronic payment services that users can use with confidence.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1024] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to search results; a means for the terminal to display search results including the reliability evaluation to the user; and a means for displaying the search results including the reliability evaluation in association with an electronic payment service. This allows the user to easily check the reliability of search results and use electronic payment services with peace of mind.

[1025] A "search engine" is a system that allows users to search for information on the Internet.

[1026] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[1027] A "server" is a computer system that processes user requests and provides the required data.

[1028] A "web page" is a collection of documents or information that is publicly available on the Internet.

[1029] A list is an ordered arrangement of things or information.

[1030] "Generative AI" refers to technology that uses artificial intelligence to analyze data and generate information.

[1031] "Content" refers to the information contained in a sentence or description.

[1032] "Analysis" is the act of examining data or information in detail to clarify its structure and meaning.

[1033] "Credibility" is an attribute that indicates how trustworthy information or data is.

[1034] "Evaluation" is the act of judging the value or quality of an object.

[1035] A "trustworthiness score" is a numerical representation of the reliability of information or data, and serves as a standard for evaluating reliability.

[1036] "Search results" are lists of related information that are displayed when a user enters a search query.

[1037] "Terminal" refers to a device such as a computer or smartphone operated by a user.

[1038] "Display" means to visually output information on a screen or display.

[1039] An "electronic payment service" is a system for conducting financial transactions over the Internet.

[1040] "Association" refers to linking multiple pieces of information or data based on some criteria.

[1041] The following describes an embodiment of the present invention. The present invention includes a system in which a user, a server, and a terminal cooperate to operate. To make it easier to understand the overall flow of the system, the specific operations at each step will be clarified.

[1042] The operation of the system is as follows.

[1043] First, a user enters a specific search query into a search engine. For example, let's say this query is "benefits of health foods." The user's device then sends this search query to the server, which communicates to the system the user's request for information.

[1044] Next, the server receives the search query submitted by the user and searches for relevant web pages based on it. The server generates a list of relevant web pages from the Internet and obtains the URL and summary of each web page. At this stage, no detailed analysis of the web page content is performed.

[1045] The server sends the content of each retrieved web page to the generation AI. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. An example of the use of generative AI is OpenAI's GPT-3 model. The generation AI generates a credibility score for each web page based on the analysis results. This credibility score is quantified (for example, on a scale from 0 to 100) and serves as a measure of trustworthiness. The server also generates a concise evaluation message based on the analysis results from the generation AI. An example message could be, "This page has a credibility score of 80."

[1046] The server then adds these credibility scores and rating messages to the search result list, thereby presenting each web page's credibility information along with the search results. Specifically, the server adds a credibility score and rating message to each item in the search result list displayed to the user.

[1047] Finally, the terminal displays the search results, including the credibility rating, to the user. The user can view the search results and check the credibility score and rating message of each web page. This system allows the user to easily determine the credibility of each web page and quickly and accurately select reliable information. Furthermore, by linking this credibility rating to electronic payment services, the user can make payments with peace of mind while checking the reliability of the transaction information.

[1048] For example, if a user enters the search query "cashback campaign," the system evaluates the reliability of the corresponding campaign site and identifies whether it is a fraudulent site. This reliability evaluation is achieved by having the server analyze the content of the campaign site using a generative AI model, calculating a reliability score, and visually displaying it to the user.

[1049] Below is an example of a prompt sentence to input to the generative AI model.

[1050] "Please rate the reliability of the following text:\n\n{text content}"

[1051] This allows users to use electronic payment services with peace of mind, while checking the reliability of transaction information, without worrying about fraud or fraudulent information.

[1052] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1053] Step 1:

[1054] A user inputs a search query into a search engine. For example, the user inputs a search query such as "effects of health foods" and clicks the search button. At this stage, the user's input is sent to the system. The input is the search query "effects of health foods," and the output is the transmission of the query information to the server.

[1055] Step 2:

[1056] The terminal sends the user's search query to the server. The terminal sends the search query entered by the user to the server as a request. The input is the user's search query, and the output is a request sent to the server.

[1057] Step 3:

[1058] The server generates a list of relevant web pages based on the user's search query. The server searches the Internet for multiple web pages related to healthy foods and obtains their URLs and summaries. The input is the user's search query, and the output is a list of relevant web pages.

[1059] Step 4:

[1060] The server sends the content of the retrieved web pages to the generation AI to evaluate their credibility. The server then sends the text content of the retrieved web pages to the generation AI for analysis. The generation AI analyzes the accuracy of terminology and the reliability of the information source. The input is the text content of the web pages, and the output is the credibility evaluation result for each web page.

[1061] Step 5:

[1062] The server calculates the reliability score of each web page based on the evaluation results of the generation AI. The server quantifies the reliability score of each web page based on the evaluation results provided by the generation AI. The reliability score is expressed in a range from 0 to 100. The input is the evaluation result of the generation AI, and the output is the reliability score.

[1063] Step 6:

[1064] The server adds a credibility score to the search results. The server assigns a credibility score and a rating message to each item in the search result list. The input is the credibility score and rating message, and the output is a search result list with the credibility rating information added.

[1065] Step 7:

[1066] The terminal displays the search results including the trustworthiness ratings to the user. The terminal visually displays the search result list including the trustworthiness ratings received from the server to the user. The input is the search result list with the trustworthiness ratings, and the output is the search result display to the user.

[1067] Step 8:

[1068] The server associates the trustworthiness rating with the electronic payment service and displays it. The server integrates the trustworthiness score and the rating message with the information of the electronic payment service involved with the user, allowing the user to confirm the trustworthiness of the transaction information. The input is search result information with the trustworthiness rating, and the output is electronic payment service information including the trustworthiness rating.

[1069] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1070] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use a search engine to obtain information. In particular, the system has the function of recognizing users' emotions and customizing search results based on those emotions. A specific embodiment of the system is described below.

[1071] First, a user enters a specific keyword into a search engine and performs a search. For example, a user enters the search query "benefits of health foods" and clicks the search button. At this stage, the user's device sends the search query to the server, and the emotion engine simultaneously analyzes the user's emotions.

[1072] The server then receives the user's search query and generates a list of relevant web pages based on it. The server retrieves the URLs and summaries of multiple web pages related to health foods from the Internet. The key here is to capture the content of each web page and prepare that information for analysis.

[1073] The server sends the content of each retrieved web page to the generation AI, which analyzes the text content of these web pages and evaluates the accuracy of terminology, the reliability of the source, etc. For example, if the generation AI analyzes a web page and determines that its content is based on a reliable source, it will assign the web page a high reliability score.

[1074] Once the analysis is complete, the server calculates a credibility score for each web page based on the evaluation results provided by the generation AI. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, "This page has a credibility score of 80."

[1075] The emotion engine then sends the results of the user's emotion analysis to the server, which then adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, the server can prioritize results with a high reliability score.

[1076] The server adds these reliability scores and rating messages to the search results. That is, the server adds reliability rating information to each item in the search result list displayed to the user. Furthermore, the server can visually highlight rating messages based on the analysis results of the emotion engine.

[1077] Finally, the user's device displays the search results, including the credibility ratings. The user can view the search results and check the credibility scores and rating messages for each web page. For example, the user's device will display a "Credibility score of 80" for each item in the "Search results for the effects of health foods" list. Furthermore, important rating messages are highlighted based on the user's sentiment.

[1078] This allows users to easily verify the reliability of web pages and accurately select reliable information without being misled by false information. This system is particularly useful for non-experts, and is a powerful tool for quickly finding reliable information from the vast amount of information on the Internet. In addition, by providing search results customized according to the user's emotions, it is possible to provide more relevant information.

[1079] The processing flow will be explained below.

[1080] Step 1:

[1081] A user enters a search query into a search engine.

[1082] The user enters search keywords into the search box on the device and clicks the search button.

[1083] Step 2:

[1084] The emotion engine analyzes the user's emotions.

[1085] The device uses an emotion engine to analyze the user's emotions based on their facial expressions and input methods.

[1086] Step 3:

[1087] The device sends the search query and sentiment analysis results to the server.

[1088] The device sends the user's search query and sentiment analysis results together to the server.

[1089] Step 4:

[1090] The server generates a list of related web pages.

[1091] The server searches for multiple relevant web pages based on the received search query and generates a list including their URLs and summaries.

[1092] Step 5:

[1093] The server retrieves the content of each web page.

[1094] The server accesses each web page based on the generated list and retrieves its HTML content.

[1095] Step 6:

[1096] The server sends the contents of the web page to the generation AI.

[1097] The server converts the content of the retrieved web page into text format and sends it to the generation AI.

[1098] Step 7:

[1099] Generative AI analyzes the content of web pages.

[1100] The generative AI analyzes the text content of the received web page and evaluates the accuracy of the terminology and the reliability of the source of information.

[1101] Step 8:

[1102] The server calculates a reliability score based on the analysis results.

[1103] Based on the evaluation results from the generation AI, the server quantifies and calculates the reliability score for each web page.

[1104] Step 9:

[1105] The server generates a reliability score and a reputation message.

[1106] The server generates a brief rating message based on the credibility score and attaches it to each web page.

[1107] Step 10:

[1108] The server adjusts the trustworthiness rating based on the emotion engine's analysis results.

[1109] The server takes into account the results of the user's sentiment analysis and adjusts the display to prioritize results with high reliability scores.

[1110] Step 11:

[1111] The server adds the authority rating to the search results.

[1112] The server adds the generated confidence score and rating message to each item in the search result list.

[1113] Step 12:

[1114] The device displays the search results, including the trustworthiness rating.

[1115] The user's device renders and displays the search results including the reliability ratings sent from the server to the user, and further highlights important rating messages based on the user's sentiment.

[1116] Example 2

[1117] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1118] Conventional search engines provide information based on search queries entered by users, but because they lack a means to evaluate the reliability of that information, it can contain inaccurate or unreliable information. Furthermore, because they provide uniform search results without taking into account the user's emotional state, it is difficult for the user to properly understand and interpret the information, which presents a challenge.

[1119] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input a search query to a search engine; a means for a terminal to transmit the search query and emotion data to the server; a means for the server to generate a list of related information based on the user's search query; a means for transmitting the content of web pages acquired by the server to a generation AI for analysis; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the emotion engine to transmit the results obtained by analyzing the user's emotions to the server; a means for the server to adjust the reliability evaluation based on the emotion analysis results; a means for adding the adjusted reliability score to the search results; and a means for the terminal to display search results including the reliability evaluation to the user. This allows the user to easily select reliable information and obtain appropriate search results according to the user's emotional state.

[1120] "User" refers to a person who uses the system to search for information.

[1121] A "search query" refers to a keyword or phrase that a user enters into a search engine.

[1122] "Terminal" refers to an electronic device used by a user to enter a search query.

[1123] "Server" refers to a central computer system that processes search queries received from users and provides relevant information.

[1124] "Emotion data" refers to data that represents the user's emotional state.

[1125] "Related information list" refers to a list of related web pages or documents generated by a server based on a search query.

[1126] "Generative AI" refers to artificial intelligence that analyzes incoming text and data and assesses its reliability.

[1127] The "trustworthiness score" is a numerical representation of the reliability of a web page or piece of information calculated by the generating AI based on the analysis results.

[1128] An "emotion engine" refers to a system that analyzes a user's emotions and generates the results.

[1129] "Reliability assessment" is a collective term for the analysis results and reliability score performed by the generative AI.

[1130] "Search results" refers to a list of relevant information provided to a user by a server, including an authority rating.

[1131] "Rating Message" refers to a brief description or message based on the credibility score.

[1132] MODE FOR CARRYING OUT THE INVENTION

[1133] The present invention provides a system that evaluates the reliability of web pages and presents the results to users when they use search engines to obtain information. This system is particularly equipped with a function to recognize users' emotions and customize search results based on those emotions.

[1134] First, a user enters a specific keyword into a search engine and performs a search. For example, the user enters "effects of health foods" and presses the search button. At this stage, the user's device sends the search query to the server. At the same time, the device uses an emotion engine to analyze the user's emotion data and also sends it to the server.

[1135] The server retrieves a list of relevant information from the Internet based on the received search query. For example, this includes the URLs of multiple web pages related to health foods and their summaries. The server then sends the content of each retrieved web page to the generation AI for analysis. The generation AI analyzes the text content of the web page and evaluates the accuracy of the terminology and the reliability of the source. For example, if the generation AI determines that a web page is based on a reliable source, it assigns the web page a high reliability score.

[1136] The analysis results are sent from the AI ​​generator to the server, which then calculates a credibility score for each web page based on the results. This credibility score is expressed as a number ranging from 0 to 100. A concise evaluation message is also generated based on the credibility score. For example, the message might say, "This page has a credibility score of 80."

[1137] The emotion engine then analyzes the user's emotional data and sends it to the server. The server receives the emotion analysis results and adjusts the reliability rating based on the results. For example, if the user expresses anxiety or excitement, it can prioritize results with a high reliability score.

[1138] Finally, the server adds these reliability scores and rating messages to the search results and sends the adjusted search results to the user's device. The device displays the search results, including the received reliability ratings, to the user. The user can view the search results and check the reliability scores and rating messages of each web page. For example, the user's device may display a "reliability score of 80" for each item in the "Search results for the effects of health foods" list. In addition, important rating messages may be highlighted based on the user's sentiment.

[1139] As a concrete example, consider a scenario in which a user searches for "benefits of health foods" and emotional data indicating "the user is currently in an anxious state" is sent to the server. The server retrieves the relevant webpage and requests analysis from the generation AI. The generation AI analyzes the webpage and generates an evaluation of "trust score 80." The emotion engine then analyzes the user's state of anxiety again and sends the result to the server. The server adjusts the display to prioritize highly reliable information for users in an anxious state. As a result, the webpage with a "trust score of 80" is displayed on the user's device.

[1140] An example of a prompt sentence might be:

[1141] "There is so much information about the effects of health foods that I'm confused. Please tell me some reliable information."

[1142] "I'd like to research the effects of health foods, but I'm not sure which information is accurate. Please give me some guidelines."

[1143] Through this system, users can not only quickly obtain reliable information, but also obtain appropriate search results according to their emotional state.

[1144] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1145] Specific explanation of processing steps

[1146] Step 1:

[1147] A user inputs a search query. For example, the user inputs the keyword "effects of health foods" into a search engine and executes a search. This input operation generates a search query.

[1148] Step 2:

[1149] The device sends the search query and emotion data to the server. The device sends the entered search query to the server, and also analyzes the user's emotion using an emotion engine and sends the data. For example, the query "Effects of health foods" and the emotion data "The user is currently feeling anxious" are sent to the server.

[1150] Step 3:

[1151] The server generates a list of relevant information based on the search query. The server searches the received search query using databases and Internet sources to generate a list of relevant web pages and documents, including URLs and summaries. For example, a list of web pages related to healthy foods is generated.

[1152] Step 4:

[1153] The server sends the retrieved webpage content to the generation AI for analysis. The server then sends the text content of the relevant webpage to the generation AI, which evaluates the accuracy of the terminology and the reliability of the source. The generation AI analyzes the received text data and performs a reliability evaluation. For example, the generation AI analyzes the content of the webpage and generates data such as "terminology accuracy 90%; source reliability 85%."

[1154] Step 5:

[1155] The server calculates a reliability score for each web page based on the analysis results. Based on the evaluation data received from the generation AI, the server calculates a reliability score for each web page. The reliability score is quantified on a scale from 0 to 100. For example, a "reliability score of 80" is calculated by combining the accuracy of the terminology and the reliability of the source of information.

[1156] Step 6:

[1157] The emotion engine analyzes the user's emotions and sends the results to the server. The emotion engine analyzes the user's emotions again and provides the results to the server. For example, the analysis result "The user is still in an anxious state" is sent to the server.

[1158] Step 7:

[1159] The server adjusts the reliability rating based on the results of emotion analysis. The server adjusts the reliability score taking into account the results of emotion analysis. If the user is expressing anxiety, the server adjusts the display so that information with a high reliability score is given priority. For example, a rule such as "for users in an anxious state, information with a reliability score of 85 or higher is given priority" is applied.

[1160] Step 8:

[1161] The server adds the adjusted credibility score and rating message to each search result item, and presents them in a user-friendly format, such as "Credit score 80" or "This page provides reliable information."

[1162] Step 9:

[1163] The terminal displays the search results to the user. The terminal displays the search results, including the reliability rating received from the server, to the user. The user can check the reliability score and rating message for each web page. For example, a list of "search results related to the effects of health foods" will display a "reliability score of 80."

[1164] This allows users to easily find reliable information and obtain appropriate search results according to their emotional state.

[1165] (Application example 2)

[1166] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1167] There is a huge amount of information on the Internet, and when users use search engines to retrieve information, it is extremely difficult to determine whether the information is reliable. Furthermore, because the ability to judge the reliability of information varies from user to user depending on their emotional and psychological state, there is a high risk of being misled by incorrect information. Therefore, there is a need for a system that allows users to quickly access more reliable information according to their emotional state.

[1168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1169] In this invention, the server includes: a means for a user to input a search query into a search engine; a means for the server to generate a list of relevant web pages based on the user's search query; a means for the server to analyze the content of the web pages using a generating AI and evaluate their reliability; a means for the server to calculate a reliability score for each web page based on the analysis results; a means for the server to add the reliability score to the search results; and a means for the terminal to display the search results including the reliability evaluation to the user and highlight them based on the user's emotions. This makes it possible to quickly provide reliable information customized according to the user's emotions.

[1170] A "search engine" is a program that searches the Internet for information based on a user-entered query and generates a list of relevant web pages.

[1171] "Generative AI" is an artificial intelligence technology that analyzes the content of web pages and evaluates their reliability.

[1172] The "trustworthiness score" is a numerical representation of the trustworthiness of a web page, and is a value evaluated by the generating AI.

[1173] "Highlighting based on emotion" is a function that analyzes the user's emotional state and displays search results in a visually striking way according to that emotion.

[1174] A "rating message" is a brief statement about the trustworthiness of a web page that is generated based on the trustworthiness score.

[1175] A "server" is a network device that receives a user's search query, generates a list of relevant web pages, and uses generation AI to obtain analysis results.

[1176] A "terminal" is an electronic device that allows a user to receive and display search results.

[1177] This invention provides a system that evaluates the reliability of information when a user retrieves information using a search engine, and customizes and displays search results based on the user's sentiment. The system includes a server, a user terminal, and several software modules.

[1178] First, a user uses their device to enter a specific keyword into a search engine. For example, they enter a keyword such as "latest security threats." This information is sent from the user's device to the server, and at the same time, an emotion engine implemented on the device analyzes the user's emotions. This emotion engine uses a library called EmotionAnalyzer.

[1179] The server then generates a list of relevant web pages based on the received search query. The server retrieves relevant web pages from the Internet using a library such as requests and prepares their content for analysis.

[1180] The server then analyzes the content of each web page using a generative AI model. This analysis evaluates the accuracy of the terminology contained in the web page and the trustworthiness of the source. Using a generative AI model library, the server generates an evaluation result and a credibility score. For example, if a web page is determined to be based on a credible source, the page is assigned a high credibility score.

[1181] Once the credibility scores and rating messages are generated, the server uses them to create a list of search results, adding a credibility score to each item. User sentiment analysis is also taken into account at this stage, and web pages with high credibility ratings are customised to be highlighted.

[1182] Finally, the user's device displays these customized search results. The user can see the credibility score and rating message for each web page. For example, if a user comments, "I'm very worried after reading the news recently," the results that are highly credible will be highlighted.

[1183] For example, the following prompt sentences are used:

[1184] "Show me an article about the latest security threats. I'm very worried about what I've read in the news lately."

[1185] This system allows users to easily find reliable information and quickly obtain appropriate information that matches their individual emotions.

[1186] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1187] Step 1:

[1188] A user enters keywords into a search engine on their device. This information is sent from the user's device to the server, and at the same time, an emotion engine on the device analyzes the user's emotions. Specifically, a user enters the search keywords "latest security threats" and comments "I feel very anxious after reading the recent news." This comment is input into the EmotionAnalyzer library, which analyzes the user's emotions. The inputs are "search keywords" and "user comments," and the output is "the user's emotional state."

[1189] Step 2:

[1190] The server searches for relevant web pages based on the search query it receives. The server uses the requests library to retrieve information from the Internet. For example, the server retrieves URLs and page contents related to "latest security threats." The input is the "search query" and the output is a "list of relevant web pages."

[1191] Step 3:

[1192] The server uses a generative AI model to analyze the content of retrieved web pages and evaluate their reliability. The generative AI model analyzes the text of each web page and evaluates the accuracy of the terminology and the reliability of the source of information. The input is a list of web pages, and the output is a reliability score and evaluation message for each web page. Specifically, the generative AI model scans the page content and uses an AI algorithm to evaluate the appropriateness of the terminology.

[1193] Step 4:

[1194] Based on the evaluation results obtained from the generative AI model, the server calculates a reliability score for each web page and generates a concise evaluation message. At the same time, it customizes the search result list according to the user's emotional state. Pages with high reliability scores are displayed preferentially. The input is a "reliability score and evaluation message," and the output is a "customized search result list." Specifically, if the user expresses anxiety, pages with high reliability scores are arranged at the top of the search results.

[1195] Step 5:

[1196] The device receives the customized search result list sent from the server and displays it to the user. The user can check the reliability scores and rating messages and select the most appropriate information. The input is the "customized search result list" and the output is the "result list displayed to the user." In concrete terms, the device visually presents the highly reliable results highlighted.

[1197] Through these processing steps, users can quickly obtain reliable information that is optimally tailored to their emotional state. For example, if a user inputs the prompt, "Show me articles about the latest security threats. I'm very anxious after reading the recent news," the system will detect the user's anxiety and highlight and display reliable security information.

[1198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1199] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1200] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1201] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1202] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1203] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1204] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1205] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1206] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1207] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1208] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1209] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1210] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1211] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1212] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1213] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1214] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1215] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1216] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1217] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1218] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1219] The following is further disclosed regarding the above embodiment.

[1220] (Claim 1)

[1221] a means for a user to input a search query into a search engine;

[1222] means for the server to generate a list of relevant web pages based on the user's search query;

[1223] A means for the server to use generated AI to analyze the content of a web page and evaluate its reliability;

[1224] A means for the server to calculate a reliability score for each web page based on the analysis results;

[1225] a means by which the server adds a confidence score to the search results;

[1226] means for the terminal to display search results including the trustworthiness assessment to the user;

[1227] A system including:

[1228] (Claim 2)

[1229] The system according to claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generation AI to analyze the accuracy of technical terms and the reliability of the information source.

[1230] (Claim 3)

[1231] 10. The system of claim 1, wherein the server further comprises means for adding a brief rating message to each web page based on the credibility score.

[1232] "Example 1"

[1233] (Claim 1)

[1234] a means for a user to input a search query into a search engine;

[1235] means for the terminal to transmit the input search query to a server;

[1236] means for the server to generate a list of relevant web pages based on the user's search query;

[1237] A means by which the server converts the contents of the web page into analyzable data;

[1238] A means for the server to use the generative AI model to analyze the content of the web page and evaluate its trustworthiness;

[1239] a means by which the generative AI model generates a confidence score and an evaluation message;

[1240] A means for the server to calculate a reliability score for each web page based on the analysis results;

[1241] a means for the server to add authority scores and rating messages to search results;

[1242] means for the terminal to display search results including the trustworthiness assessment to the user;

[1243] A system including:

[1244] (Claim 2)

[1245] The system of claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generative AI model to analyze the accuracy of terminology and the reliability of the information source.

[1246] (Claim 3)

[1247] 10. The system of claim 1, wherein the server further comprises means for adding a brief rating message to each web page based on the credibility score.

[1248] "Application Example 1"

[1249] (Claim 1)

[1250] a means for a user to input a search query into a search engine;

[1251] means for the server to generate a list of relevant web pages based on the user's search query;

[1252] A means for the server to use generated AI to analyze the content of a web page and evaluate its reliability;

[1253] A means for the server to calculate a reliability score for each web page based on the analysis results;

[1254] a means by which the server adds a confidence score to the search results;

[1255] means for the terminal to display search results including the trustworthiness assessment to the user;

[1256] a means for displaying search results including a reliability assessment in association with an electronic payment service;

[1257] A system including:

[1258] (Claim 2)

[1259] The system according to claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generation AI to analyze the accuracy of technical terms and the reliability of the information source.

[1260] (Claim 3)

[1261] 10. The system of claim 1, further comprising: means for adding a brief rating message to each web page based on the credibility score.

[1262] "Example 2: Combining Emotion Engines"

[1263] (Claim 1)

[1264] a means for a user to input a search query into a search engine;

[1265] a means for the device to transmit the search query and emotion data to a server;

[1266] means for the server to generate a list of relevant information based on the user's search query;

[1267] A means for transmitting the content of the web page acquired by the server to the generation AI for analysis;

[1268] A means for the server to calculate a reliability score for each web page based on the analysis results;

[1269] means for transmitting the result obtained by the emotion engine analyzing the emotion of the user to a server;

[1270] a means for the server to adjust the trustworthiness rating based on the sentiment analysis result;

[1271] a means for adding a server-adjusted confidence score to the search results;

[1272] means for the terminal to display search results including the trustworthiness assessment to the user;

[1273] A system including:

[1274] (Claim 2)

[1275] The system according to claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generation AI and having the AI ​​analyze the accuracy and reliability of the information.

[1276] (Claim 3)

[1277] 10. The system of claim 1, further comprising means for the server to add a brief rating message to each web page based on the confidence score and visually highlight based on the results of the sentiment engine.

[1278] "Application example 2 when combining emotion engines"

[1279] (Claim 1)

[1280] a means for a user to input a search query into a search engine;

[1281] means for the server to generate a list of relevant web pages based on the user's search query;

[1282] A means for the server to use generated AI to analyze the content of a web page and evaluate its reliability;

[1283] A means for the server to calculate a reliability score for each web page based on the analysis results;

[1284] a means by which the server adds a confidence score to the search results;

[1285] a means for displaying search results including a reliability rating to a user and highlighting the results based on the user's sentiment;

[1286] A system including:

[1287] (Claim 2)

[1288] The system according to claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generation AI to analyze the accuracy of technical terms and the reliability of the information source.

[1289] (Claim 3)

[1290] 10. The system of claim 1, further comprising means for the server to add a brief rating message to each web page based on the credibility score and to customize search results based on user sentiment. [Explanation of symbols]

[1291] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input a search query into a search engine; means for the server to generate a list of relevant web pages based on the user's search query; A means for the server to use generated AI to analyze the content of a web page and evaluate its reliability; A means for the server to calculate a reliability score for each web page based on the analysis results; a means by which the server adds a confidence score to the search results; means for the terminal to display search results including the trustworthiness assessment to the user; A system including:

2. The system according to claim 1, further comprising means for transmitting the content of the web page acquired by the server to the generation AI and for analyzing the accuracy of technical terms and the reliability of the information source.

3. 10. The system of claim 1, further comprising means for the server to add a brief rating message to each web page based on the credibility score.

Images